© 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. 88607
    Prev
    Next
    INDEX
    Explanations

    scientific studies

    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
    ä¹ŁçŁ¥éģĵ
    -0.27
    åĢĴåľ¨åľ°
    -0.26
     legalization
    -0.26
    Foreign
    -0.25
     warranted
    -0.25
     deserved
    -0.25
    好æ¶Īæģ¯
    -0.25
    UFF
    -0.24
    åĬ£åĬ¿
    -0.23
     logfile
    -0.23
    POSITIVE LOGITS
    ISCO
    0.26
    ously
    0.26
     directly
    0.25
    rine
    0.24
    äºĴåĬ©
    0.24
     pac
    0.23
    atures
    0.23
    åĽŀäºĭ
    0.23
     ind
    0.23
     precise
    0.23
    Activations Density 0.008%

    No Known Activations