© 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. 98038
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    éļ¾éģĵ
    -0.28
    ç»ĻåŃ©åŃIJ
    -0.25
    ì°¨
    -0.24
     ####
    -0.23
     break
    -0.23
     willingly
    -0.23
    æµĬ
    -0.23
     given
    -0.23
    ESIS
    -0.23
    dziaÅĤ
    -0.23
    POSITIVE LOGITS
    ĸī
    0.26
    mmas
    0.25
    '+↵
    0.23
     PHI
    0.23
    tas
    0.23
    anked
    0.23
    æĬ¥
    0.23
    itori
    0.23
    éĢĤå®ľ
    0.23
     Rewards
    0.22
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.