© 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. 87186
    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
    skip
    -0.28
     Contributions
    -0.28
    oj
    -0.27
    iaux
    -0.25
    are
    -0.25
     Assertions
    -0.24
    éĺģ
    -0.24
    span
    -0.24
    outs
    -0.24
    opes
    -0.24
    POSITIVE LOGITS
    溶解
    0.27
    iéndo
    0.27
     mastur
    0.27
    IDEO
    0.26
    HER
    0.26
    ä¸Ģéģĵ
    0.26
    LEM
    0.26
     dó
    0.26
     vö
    0.25
    iếc
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.