© 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. 129955
    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
    客æĪ·æľįåĬ¡
    -0.28
    anga
    -0.28
    curity
    -0.27
    icing
    -0.25
    .BackgroundImage
    -0.25
    bum
    -0.24
    è¾ħ导
    -0.24
    åIJĪä¸Ģ
    -0.24
    elper
    -0.24
    并
    -0.24
    POSITIVE LOGITS
    æĬĵ好
    0.28
    Repo
    0.25
    訴
    0.24
    tab
    0.23
     types
    0.23
    åĢ¨
    0.23
     ==↵
    0.23
    _crypto
    0.23
    ä¸Ģçīĩ
    0.23
    _handlers
    0.23
    Activations Density 0.007%

    No Known Activations

    This feature has no known activations.