© 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. 141324
    Prev
    Next
    INDEX
    Explanations

    Numerical data

    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
    ä¸ĢåĽŀäºĭ
    -0.27
    产çī©
    -0.25
    orget
    -0.25
     invol
    -0.25
    abar
    -0.25
    çĸ
    -0.24
     deÄŁildir
    -0.24
     rhet
    -0.24
    åĽŀäºĭ
    -0.24
    jian
    -0.24
    POSITIVE LOGITS
    åıįä¹ĭ
    0.26
    çĪ±å¥½
    0.26
    ead
    0.26
    elo
    0.26
     Rec
    0.26
    blind
    0.25
     Uph
    0.24
     odds
    0.24
     blind
    0.24
    .getAs
    0.24
    Activations Density 19.789%

    No Known Activations