© 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. 129935
    Prev
    Next
    INDEX
    Explanations

    coding

    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
     [
    -0.25
    æĿ¥è®²
    -0.24
    Exports
    -0.24
    abo
    -0.24
    é¤Ĭ
    -0.24
    ban
    -0.24
    amente
    -0.24
    åħ»æĪIJ
    -0.24
     Pull
    -0.23
    inaire
    -0.23
    POSITIVE LOGITS
    singular
    0.25
     labeled
    0.25
    çķĮçļĦ
    0.24
    HTTPRequest
    0.23
     AngularFire
    0.22
     labeling
    0.22
    edReader
    0.21
    æĮģèĤ¡
    0.21
    FONT
    0.21
     misrepresented
    0.21
    Activations Density 0.110%

    No Known Activations