© 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. 111432
    Prev
    Next
    INDEX
    Explanations

    Programming questions and answers

    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
    èĨı
    -0.25
    ĻĤ
    -0.24
    ugal
    -0.24
    raq
    -0.24
    è·ļ
    -0.23
    .RunWith
    -0.23
    çĺ«
    -0.23
    BODY
    -0.23
    endregion
    -0.23
    ele
    -0.23
    POSITIVE LOGITS
    ä¼¼ä¹İæĺ¯
    0.27
    ces
    0.27
     bullshit
    0.25
    chos
    0.25
    åĢ¾
    0.24
    اخ
    0.24
     screwed
    0.24
     samt
    0.24
     charms
    0.23
    ç»ĻæĤ¨
    0.23
    Activations Density 0.015%

    No Known Activations