© 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. 87509
    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
    ä»»ä½ķæŶåĢĻ
    -0.30
    aly
    -0.29
    ä¹İ
    -0.28
    说çļĦæĺ¯
    -0.25
    .pb
    -0.25
    onym
    -0.24
    å°±åľ¨äºİ
    -0.24
    亦
    -0.24
    åIJ¹
    -0.24
     disag
    -0.24
    POSITIVE LOGITS
    'O
    0.28
    èĪ±
    0.27
    ï¼ļ<
    0.26
    uits
    0.25
    "),"
    0.25
    åĽ½äºº
    0.25
    neys
    0.25
     dequeue
    0.24
    ogne
    0.24
     responseBody
    0.23
    Activations Density 0.004%

    No Known Activations