© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 30-TRANSCODER-HP
    7. 96497
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ToOne
    -0.25
    çĶ¨æĪ·åIJį
    -0.24
    GridLayout
    -0.24
     appropriated
    -0.24
    ////////////////////////////////////////////////////////////////////////////////↵
    -0.24
    landers
    -0.24
    .getBlock
    -0.24
    iza
    -0.24
    åĮºåĿĹ
    -0.23
    ustum
    -0.23
    POSITIVE LOGITS
    ohl
    0.30
    æĮĤåı·
    0.27
    çŃIJ
    0.25
    zo
    0.25
    æīĺ
    0.25
     Cecil
    0.25
    ordo
    0.24
     civil
    0.24
    许
    0.24
    ä¸Ģè¾ĪåŃIJ
    0.24
    Activations Density 0.882%

    No Known Activations

    This feature has no known activations.