© 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. 111967
    Prev
    Next
    INDEX
    Explanations

    9

    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
     wards
    -0.31
    ToDate
    -0.28
    eph
    -0.25
     assured
    -0.25
    å½ĵä¹ĭ
    -0.25
     iphone
    -0.24
    iei
    -0.23
    åIJĪèµĦ
    -0.23
    thing
    -0.23
    ToPoint
    -0.23
    POSITIVE LOGITS
     Syntax
    0.27
     greatly
    0.25
    åªĴ
    0.25
     tw
    0.24
     кап
    0.23
    BuilderFactory
    0.23
    æĬ¬èµ·
    0.23
    ÑĤай
    0.23
    å¾Ī好
    0.23
     Apost
    0.22
    Activations Density 0.079%

    No Known Activations