© 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. 41250
    Prev
    Next
    INDEX
    Explanations

    Mal

    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
    lds
    -0.27
    айн
    -0.26
    _attrib
    -0.26
    ijn
    -0.26
    éĿ¢åĮħ
    -0.25
    æ³°å±±
    -0.25
    lijah
    -0.25
    Fac
    -0.25
     Dere
    -0.25
    SEN
    -0.25
    POSITIVE LOGITS
    ActionTypes
    0.28
    illet
    0.27
     melt
    0.27
     mel
    0.27
    åıªåī©ä¸ĭ
    0.27
    ãİŀ
    0.27
     BaseModel
    0.25
    OLT
    0.25
    god
    0.25
    icism
    0.25
    Activations Density 0.002%

    No Known Activations