© 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. 24-TRANSCODER-HP
    7. 149938
    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_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stry
    -0.27
    idy
    -0.26
    ency
    -0.26
    _DECLARE
    -0.25
    activation
    -0.24
    æĥ³èµ·äºĨ
    -0.24
    umd
    -0.24
    ony
    -0.24
    zones
    -0.24
    cimiento
    -0.24
    POSITIVE LOGITS
    åIJ¦å®ļ
    0.29
     discount
    0.28
     afford
    0.25
     Voor
    0.25
    æĬµ
    0.25
    ä¸Ģ份
    0.25
    åħŃ个
    0.25
    ANCEL
    0.25
     compound
    0.24
    åĽŀéģ¿
    0.24
    Activations Density 0.972%

    No Known Activations