© 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. 35-TRANSCODER-HP
    7. 40350
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ID
    -0.28
    Field
    -0.27
    apid
    -0.26
    UP
    -0.25
    bourne
    -0.24
     camp
    -0.24
    abis
    -0.24
     easily
    -0.23
    ru
    -0.23
    wa
    -0.23
    POSITIVE LOGITS
    isia
    0.27
    körper
    0.26
    -linux
    0.24
    ảo
    0.24
    åĴĮå¹³
    0.24
    -loop
    0.24
     LOOP
    0.24
    edar
    0.24
    éĿĵ
    0.24
    TEGER
    0.24
    Activations Density 5.218%

    No Known Activations

    This feature has no known activations.