© 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. 41649
    Prev
    Next
    INDEX
    Explanations

    Negation

    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
    ç©¿
    -0.28
    è··
    -0.26
    å¡«è¡¥
    -0.25
    åģĩåĨĴ
    -0.25
    ItemImage
    -0.24
     compensated
    -0.24
    sted
    -0.24
     compens
    -0.24
    pei
    -0.24
    éĻĦ
    -0.24
    POSITIVE LOGITS
    loff
    0.30
    åĩĨ
    0.28
    æĭ¢
    0.27
    eca
    0.25
    Rule
    0.25
    æŁ½
    0.24
    iembre
    0.24
     CONDITIONS
    0.24
    lius
    0.24
    _flg
    0.24
    Activations Density 0.001%

    No Known Activations