© 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. 98152
    Prev
    Next
    INDEX
    Explanations

    Single

    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
    ĺ认
    -0.28
     regular
    -0.28
    äºĮæľŁ
    -0.26
     ÑĢеÑĪи
    -0.26
    åįķä¸Ģ
    -0.26
    ilinear
    -0.25
    ieux
    -0.25
    ä½łè§īå¾Ĺ
    -0.25
    ignite
    -0.25
     regularization
    -0.24
    POSITIVE LOGITS
    ESA
    0.28
     m
    0.25
     sunk
    0.25
    Broad
    0.25
     alternatively
    0.24
     Strait
    0.24
    PIC
    0.24
    TMP
    0.24
     PIC
    0.24
     verbally
    0.24
    Activations Density 0.043%

    No Known Activations