© 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. 112142
    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
    äºĴåĪ©
    -0.26
    仪
    -0.26
    etr
    -0.26
    äºİæĺ¯æĪij
    -0.25
    ç´łè´¨
    -0.25
    GRESS
    -0.25
     Len
    -0.25
    å¹´ä¹ĭ
    -0.24
    лÑĮн
    -0.24
    irst
    -0.24
    POSITIVE LOGITS
    include
    0.26
    \Bridge
    0.25
    ำ
    0.25
    ção
    0.25
    cba
    0.23
    ças
    0.23
    éĿŀçī©è´¨
    0.23
    -devel
    0.23
    JEXEC
    0.23
    æī©å¤§
    0.23
    Activations Density 0.020%

    No Known Activations

    This feature has no known activations.