© 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. 108393
    Prev
    Next
    INDEX
    Explanations

    Technical specifications and configurations

    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
    (||
    -0.29
    çı²
    -0.27
     mechanics
    -0.26
    oes
    -0.24
     unst
    -0.24
    ibil
    -0.24
    åIJĦè¡Į
    -0.24
    çĹķ
    -0.24
    ilio
    -0.24
    normalize
    -0.24
    POSITIVE LOGITS
    ç²¾éĢī
    0.33
    æĽ¿æį¢
    0.32
    éĢī
    0.31
     selected
    0.30
     Selection
    0.30
     sources
    0.30
    éĢīæĭ©
    0.29
    éģ¸æĵĩ
    0.29
    ulet
    0.29
    æĽ¿ä»£
    0.29
    Activations Density 49.347%

    No Known Activations