© 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. 41950
    Prev
    Next
    INDEX
    Explanations

    Yes

    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
    ")+
    -0.30
     Sure
    -0.28
     sure
    -0.28
    ï¼ļ"+
    -0.27
    Sure
    -0.27
    sure
    -0.26
    ()."
    -0.26
    EXPORT
    -0.26
    ()+"
    -0.25
    Äł
    -0.25
    POSITIVE LOGITS
    --
    0.46
     --
    0.43
    ---
    0.40
    ,
    0.37
    —
    0.36
     ---
    0.34
    ----
    0.33
    âĶĢ
    0.32
     that
    0.30
     —
    0.29
    Activations Density 0.005%

    No Known Activations