© 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. 112394
    Prev
    Next
    INDEX
    Explanations

    Hayden

    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
    .ant
    -0.28
    èĻ¢
    -0.26
    loff
    -0.25
    èĪªçıŃ
    -0.25
     antib
    -0.25
     dish
    -0.25
    jab
    -0.25
     Gree
    -0.24
     ant
    -0.24
    fac
    -0.24
    POSITIVE LOGITS
    iram
    0.28
    etry
    0.27
    onium
    0.26
    phis
    0.26
    itan
    0.25
    erin
    0.24
    istrate
    0.24
    Queryable
    0.23
    ’n
    0.23
     Pir
    0.23
    Activations Density 0.011%

    No Known Activations