© 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. 88251
    Prev
    Next
    INDEX
    Explanations

    Numbers

    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
    icator
    -0.28
    pire
    -0.26
    udge
    -0.26
    ciÄħ
    -0.25
    ubar
    -0.25
    umb
    -0.24
    ciÄħg
    -0.24
    urses
    -0.24
    umberland
    -0.23
    olon
    -0.23
    POSITIVE LOGITS
    ä¸ĸ纪
    0.32
    幸
    0.25
    ement
    0.25
    è¦ģæľī
    0.24
     dep
    0.24
    ahl
    0.24
    serial
    0.23
    è¦ģåģļåĪ°
    0.23
    å¢ŀ
    0.23
    èĮģ
    0.23
    Activations Density 0.325%

    No Known Activations