© 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. 20-TRANSCODER-HP
    7. 129497
    Prev
    Next
    INDEX
    Explanations

    negative consequences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĶ±ä¸ŃåĽ½
    -0.30
    纸ä¸Ĭ
    -0.28
    çĿģ
    -0.27
    迸
    -0.26
    éĢļåħ³
    -0.26
    ä¸įäºĨ
    -0.25
    frog
    -0.25
    ä¹Łåıªèĥ½
    -0.24
    åıĪè¦ģ
    -0.24
     Editors
    -0.24
    POSITIVE LOGITS
    traits
    0.27
    ooke
    0.26
    avers
    0.25
    aid
    0.24
     substr
    0.24
    makt
    0.24
    fen
    0.24
    riage
    0.24
    traction
    0.24
    ç¥ī
    0.23
    Activations Density 10.241%

    No Known Activations