© 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. 39327
    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
    Reviewed
    -0.27
    ]int
    -0.27
     Baths
    -0.27
    çŃĴ
    -0.27
    á»ĵn
    -0.25
     inex
    -0.25
    ucker
    -0.24
     Pun
    -0.24
     Confeder
    -0.24
     sanction
    -0.24
    POSITIVE LOGITS
    conduct
    0.31
     conducting
    0.28
     Conduct
    0.28
    åı¸æ³ķ
    0.27
     crib
    0.27
    =cut
    0.26
    åı¯è§Ĩ
    0.26
    nit
    0.25
    ×ļ
    0.25
     conduct
    0.25
    Activations Density 0.016%

    No Known Activations

    This feature has no known activations.