© 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. 107448
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    akis
    -0.27
    equiv
    -0.26
     approach
    -0.26
     main
    -0.26
     straight
    -0.26
    å¾Ĺ好
    -0.25
    ively
    -0.25
    å±ı
    -0.24
    screen
    -0.24
    亿ä¸ĩ
    -0.24
    POSITIVE LOGITS
     FAG
    0.26
    nis
    0.26
    ħį
    0.25
    ,nil
    0.25
    ç¢İ
    0.25
     |--
    0.23
    ccione
    0.23
     stringstream
    0.23
    ARSE
    0.23
    oppable
    0.23
    Activations Density 3.447%

    No Known Activations

    This feature has no known activations.