© 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. 130763
    Prev
    Next
    INDEX
    Explanations

    as

    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
    ockey
    -0.26
    çłŃ
    -0.25
    骢
    -0.25
    omin
    -0.25
    åĢŁéĴ±
    -0.24
     candidacy
    -0.24
    èı©æıIJ
    -0.23
     coincidence
    -0.23
    丹
    -0.23
     Careers
    -0.23
    POSITIVE LOGITS
     lead
    0.29
    xec
    0.27
     active
    0.27
    esser
    0.27
    urst
    0.26
    -Pack
    0.26
     well
    0.26
    bard
    0.26
    apsed
    0.26
    åĨ³
    0.25
    Activations Density 0.111%

    No Known Activations