© 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
    2. Qwen3-4B
    3. 20-TRANSCODER-HP
    4. 107377
    Prev
    Next
    INDEX
    Explanations

    Editing and content creation

    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
    resco
    -0.26
    raries
    -0.26
    backs
    -0.26
     backs
    -0.26
    inters
    -0.25
    pires
    -0.25
     sık
    -0.25
    è½½ä½ĵ
    -0.24
     Swe
    -0.23
     <<"
    -0.23
    POSITIVE LOGITS
    åĮ¡
    0.29
    atura
    0.27
    讨
    0.26
    çĽĤ
    0.26
    _xx
    0.26
    顺åºĶ
    0.26
    .HasValue
    0.25
    ence
    0.24
    ament
    0.24
    encer
    0.24
    Activations Density 6.011%

    No Known Activations