© 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. 39441
    Prev
    Next
    INDEX
    Explanations

    attention deficit

    np_max-act-logits · gemini-2.0-flash
    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
     Soil
    -0.29
    SO
    -0.28
    TS
    -0.28
    CO
    -0.27
    olved
    -0.27
     Со
    -0.27
     Same
    -0.26
     Civic
    -0.26
    CI
    -0.26
    SI
    -0.26
    POSITIVE LOGITS
    -days
    0.37
    -invalid
    0.35
     inconsistency
    0.34
    -percent
    0.33
    -placement
    0.33
    -hours
    0.32
    -lines
    0.32
    -spacing
    0.32
    -density
    0.32
    -blocking
    0.32
    Activations Density 0.070%

    No Known Activations