© 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. 63574
    Prev
    Next
    INDEX
    Explanations

    back

    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
    vect
    -0.27
    xr
    -0.26
     precedence
    -0.26
    æķ°ç»Ħ
    -0.25
     vect
    -0.25
    æĬĵ
    -0.25
    åıĺæį¢
    -0.25
     çĽ
    -0.24
    å¹´çĶ±
    -0.24
    身形
    -0.24
    POSITIVE LOGITS
    åļ¼
    0.28
    ç»Ļ她
    0.27
    ogn
    0.27
     Curtain
    0.26
    åĨįæĿ¥
    0.26
    roots
    0.25
    ,nil
    0.25
    è¿ĩé«ĺ
    0.24
    ihar
    0.24
    严éĩįå½±åĵį
    0.23
    Activations Density 14.188%

    No Known Activations