© 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. 39638
    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
    forge
    -0.25
    æħij
    -0.25
    cott
    -0.23
    âĢ¢↵↵
    -0.23
     erection
    -0.23
     rests
    -0.22
    ivering
    -0.22
    å¤ļä¸ĩ
    -0.22
    åľ¨é¦Ļ港
    -0.22
    .opts
    -0.22
    POSITIVE LOGITS
    ape
    0.27
    è§Ħ
    0.26
    ofil
    0.25
     Flo
    0.25
    è§Ĥ
    0.25
    ä¿®æŃ£
    0.25
    è§ĦåĪĻ
    0.24
    Plate
    0.23
     Nic
    0.23
    monds
    0.23
    Activations Density 0.858%

    No Known Activations

    This feature has no known activations.