© 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. 41613
    Prev
    Next
    INDEX
    Explanations

    Forced actions/relocations

    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
    moving
    -0.32
     moving
    -0.32
     Moving
    -0.28
    移åĪ°
    -0.28
    psc
    -0.28
    读åIJİ
    -0.28
    iy
    -0.28
     driving
    -0.27
     refuse
    -0.27
     MOVE
    -0.26
    POSITIVE LOGITS
    æĭľ
    0.32
    .ak
    0.29
    æIJĶ
    0.28
    _tac
    0.26
    åīĸ
    0.26
    çľĭå¾ħ
    0.25
     Tur
    0.24
    æīĵæī«
    0.24
    hores
    0.24
    建ç«ĭåģ¥åħ¨
    0.24
    Activations Density 0.000%

    No Known Activations