© 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. 129954
    Prev
    Next
    INDEX
    Explanations

    computer code and usage

    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
    æĻĸ
    -0.27
    æ»ļ
    -0.27
    annotate
    -0.26
    èĪį
    -0.25
    èĪĶ
    -0.24
    Increase
    -0.24
     Increase
    -0.24
    â¬ĩ
    -0.24
    CP
    -0.24
     ÑĢазнÑĭÑħ
    -0.24
    POSITIVE LOGITS
    è¯ļå®ŀ
    0.28
    atta
    0.26
    rear
    0.26
    æĩĤ
    0.25
    atas
    0.25
    icode
    0.25
    çļĦåŃĺåľ¨
    0.25
     absolute
    0.25
    ordinary
    0.24
    imeter
    0.24
    Activations Density 0.006%

    No Known Activations