© 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. 111615
    Prev
    Next
    INDEX
    Explanations

    all, any

    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
    ante
    -0.29
    ANTE
    -0.29
    æıĴ
    -0.26
     pe
    -0.25
     grate
    -0.25
     feu
    -0.24
     buy
    -0.24
    æİĮæı¡
    -0.24
     ê²
    -0.24
     ÑĥÑģл
    -0.24
    POSITIVE LOGITS
    oda
    0.26
    odic
    0.25
    ãģĻãĤĮãģ°
    0.24
    FSIZE
    0.24
     Depot
    0.24
    asics
    0.24
    åĴĮ个人
    0.23
     sensible
    0.23
    ï¼ĮåĪĻ
    0.23
    :Is
    0.23
    Activations Density 0.013%

    No Known Activations