© 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. 141006
    Prev
    Next
    INDEX
    Explanations

    Intensifiers/Qualifiers

    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
    åľ°çľĭçĿĢ
    -0.26
    abler
    -0.26
    ö
    -0.26
    ç»ıåħ¸çļĦ
    -0.25
    nga
    -0.25
    åĨĻçĿĢ
    -0.25
    CLAIM
    -0.25
     herr
    -0.24
    (map
    -0.24
    代表æĢ§
    -0.24
    POSITIVE LOGITS
    ottom
    0.30
     gratuitement
    0.27
    itin
    0.26
    lein
    0.25
    ,filename
    0.25
    é¢Ľ
    0.25
     Verified
    0.25
    é»ĺ
    0.25
    toupper
    0.25
    ichel
    0.25
    Activations Density 23.923%

    No Known Activations