© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 87113
    Prev
    Next
    INDEX
    Explanations

    Formatting code

    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
    çķĻä¸ĭæĿ¥
    -0.25
    è³ĵ
    -0.25
    çļĦè¯Ŀ
    -0.25
    æ·±å±Ĥ次
    -0.24
    '))↵↵↵
    -0.24
    çļĩ
    -0.24
    åIJ«ä¹ī
    -0.24
    æĦıæĢĿ
    -0.23
    æĤĦ
    -0.23
    ä»ĵ
    -0.23
    POSITIVE LOGITS
    assoc
    0.28
    unken
    0.27
    erior
    0.26
    icies
    0.26
    KC
    0.25
    tridges
    0.25
    tracts
    0.24
    fcc
    0.24
    RAFT
    0.24
    oki
    0.24
    Activations Density 0.002%

    No Known Activations