© 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. 25-TRANSCODER-HP
    7. 108678
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omers
    -0.27
    æ·±åĪ»
    -0.27
    ande
    -0.25
    ë°°
    -0.25
    åĮħåĮħ
    -0.25
     texas
    -0.25
    isa
    -0.24
    èī¯ãģĭãģ£ãģŁ
    -0.23
    ucion
    -0.23
    _zones
    -0.23
    POSITIVE LOGITS
    ngle
    0.26
    .ctrl
    0.26
     kitty
    0.25
     Vern
    0.24
     benefici
    0.24
    ennis
    0.24
    æ·«
    0.23
    æĦıè§ģåıįé¦Ī
    0.23
    onis
    0.23
    cope
    0.23
    Activations Density 1.388%

    No Known Activations

    This feature has no known activations.