© 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. 32-TRANSCODER-HP
    7. 43232
    Prev
    Next
    INDEX
    Explanations

    Technical writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÑĦеÑĢ
    -0.28
    è½½
    -0.27
     sala
    -0.27
    çªĿ
    -0.26
     Humb
    -0.26
    (system
    -0.26
    ç³»ç»Ł
    -0.25
    nb
    -0.25
    èĤ¥
    -0.25
     Hint
    -0.25
    POSITIVE LOGITS
    åĵįåºĶ
    0.39
     response
    0.39
     reflection
    0.38
    reflection
    0.36
     reaction
    0.36
    åıįåºĶ
    0.36
     Reaction
    0.35
     Response
    0.35
     responses
    0.33
    Reaction
    0.31
    Activations Density 0.000%

    No Known Activations