© 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. 87562
    Prev
    Next
    INDEX
    Explanations

    and

    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
    oret
    -0.33
    ĭ
    -0.24
    Ñīен
    -0.24
    èĢĮå·²
    -0.24
    åħ
    -0.23
    -Sah
    -0.23
     perhaps
    -0.23
    "↵↵
    -0.23
    å¯Ĥ
    -0.23
    infinity
    -0.23
    POSITIVE LOGITS
    itted
    0.24
    ardy
    0.24
    ç½²
    0.24
    .setScale
    0.23
    gradable
    0.23
    *</
    0.23
    ï¼ļ<
    0.23
    Collapse
    0.23
    ï¼ļ</
    0.23
     Parad
    0.23
    Activations Density 0.006%

    No Known Activations