© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7182
    Prev
    Next
    INDEX
    Explanations

    Something being seen/visible

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    失è°ĥ
    -0.26
    åıªä¸º
    -0.25
    COVERY
    -0.25
     mah
    -0.25
    åĨįåĪ°
    -0.24
    æĿ¥çľĭçľĭ
    -0.24
     ×ŀ×Ĵ
    -0.24
    lexer
    -0.24
    ahrenheit
    -0.24
    -tier
    -0.23
    POSITIVE LOGITS
    shall
    0.28
     independence
    0.27
    Independ
    0.26
    ä¸ĢåĽŀäºĭ
    0.25
     Independence
    0.25
    expect
    0.24
    elman
    0.24
    rine
    0.23
     Ordered
    0.23
    sten
    0.23
    Activations Density 0.008%

    No Known Activations