© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 142491
    Prev
    Next
    INDEX
    Explanations

    code and languages

    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
    Negative Logits
    åħ¶å®ĥéĹ®é¢ĺ
    -0.28
     Kad
    -0.26
     dispenser
    -0.26
     Jury
    -0.24
     jury
    -0.24
     sampled
    -0.23
     param
    -0.23
    cej
    -0.23
     Prosecutor
    -0.23
    -pill
    -0.22
    POSITIVE LOGITS
    å¤ĸç±į
    0.28
     wards
    0.26
    wards
    0.25
    Indented
    0.24
    Es
    0.24
    aby
    0.24
    ë°ľ
    0.24
    hat
    0.24
    Hat
    0.23
    foot
    0.23
    Activations Density 5.424%

    No Known Activations