© 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. 39812
    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
    oodle
    -0.28
     sol
    -0.25
    西äºļ
    -0.25
    æ·Į
    -0.24
     sint
    -0.24
    éĿ¢èī²
    -0.24
     substantive
    -0.24
     salary
    -0.24
    åĢŁ
    -0.24
    edata
    -0.24
    POSITIVE LOGITS
    atron
    0.31
    */)
    0.27
    éĨ®
    0.26
    éĺī
    0.26
    ADF
    0.25
    istrator
    0.25
    ancell
    0.24
    atz
    0.24
    acco
    0.24
    ronics
    0.24
    Activations Density 23.361%

    No Known Activations

    This feature has no known activations.