© 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. 41212
    Prev
    Next
    INDEX
    Explanations

    short

    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
     stranger
    -0.27
    folio
    -0.26
    代çIJĨ人
    -0.26
    大çĨĬçĮ«
    -0.26
    xec
    -0.25
    à¤ĭ
    -0.25
    -corner
    -0.24
    VRT
    -0.24
     jewish
    -0.23
    reas
    -0.23
    POSITIVE LOGITS
    eties
    0.28
    iny
    0.27
    bff
    0.27
    ละ
    0.26
     Ñģимвол
    0.25
    -s
    0.25
    bbc
    0.25
    enen
    0.25
    bx
    0.24
    ä¹ĭéĹ´çļĦ
    0.24
    Activations Density 0.002%

    No Known Activations