© 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. 39498
    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
    强åĬ¿
    -0.25
    èµ°è¿ij
    -0.25
    gran
    -0.24
    ç¾½
    -0.24
    ä¿©
    -0.24
    ',...↵
    -0.23
     Reads
    -0.23
    angel
    -0.23
    attended
    -0.23
    >',↵
    -0.23
    POSITIVE LOGITS
    Ïį
    0.26
    çļĦä¿¡å¿ĥ
    0.23
     jakoÅĽci
    0.23
    EXPORT
    0.23
     consciousness
    0.23
    è¤Ĭ
    0.23
    /arch
    0.23
    ongoose
    0.23
    æĪijè®°å¾Ĺ
    0.22
     kijken
    0.22
    Activations Density 8.429%

    No Known Activations

    This feature has no known activations.