© 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. 129610
    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
     cach
    -0.26
     rdr
    -0.24
    å§Ķ
    -0.24
     trop
    -0.23
    feeds
    -0.23
     entrev
    -0.23
     athlete
    -0.23
     strstr
    -0.23
    "strconv
    -0.22
    chem
    -0.22
    POSITIVE LOGITS
    ма
    0.27
    æīĭèħķ
    0.26
    =result
    0.26
    lös
    0.26
    uers
    0.25
    è¿Ļ家ä¼Ļ
    0.25
    èĮĥ
    0.25
    /popper
    0.25
    æŃĻ
    0.25
     punch
    0.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.