© 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. 22-TRANSCODER-HP
    7. 88531
    Prev
    Next
    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çIJĨ论ä¸Ĭ
    -0.32
     theoretically
    -0.27
    rier
    -0.26
    ä¸į论æĺ¯
    -0.26
     days
    -0.26
     Official
    -0.25
    кла
    -0.25
    Unchecked
    -0.24
     nowhere
    -0.24
    åĽĬ
    -0.23
    POSITIVE LOGITS
    udent
    0.29
    æĿī
    0.28
    象
    0.28
    plash
    0.27
    åĥı
    0.27
    dez
    0.26
    aman
    0.26
    _DIAG
    0.26
    ableView
    0.25
    dek
    0.25
    Activations Density 0.026%

    No Known Activations