© 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. 43224
    Prev
    Next
    INDEX
    Explanations

    ,

    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
    缣
    -0.35
     holland
    -0.26
    olla
    -0.24
    holm
    -0.24
    污
    -0.24
     compound
    -0.24
    ãĥŃãĥ¼
    -0.24
    erts
    -0.24
    ourg
    -0.24
    Ĥæķ°
    -0.24
    POSITIVE LOGITS
    ativos
    0.31
    .nn
    0.30
    zip
    0.28
    avel
    0.25
    ublic
    0.25
    ativo
    0.24
    atars
    0.24
    bucks
    0.24
     Drive
    0.23
     si
    0.23
    Activations Density 0.002%

    No Known Activations