© 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. 87450
    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
    andle
    -0.23
     neuro
    -0.23
    ;base
    -0.23
    trie
    -0.23
    mens
    -0.23
    æĦĨ
    -0.23
    eacher
    -0.22
    guid
    -0.22
    åķ¶
    -0.22
     EN
    -0.22
    POSITIVE LOGITS
    LECT
    0.26
    åªĽ
    0.26
     rocker
    0.25
    è¯Ŀé¢ĺ
    0.25
    ä¿ĥ
    0.24
    Topics
    0.24
    xcf
    0.23
     politic
    0.23
    æĶ¶èĹı
    0.23
    LT
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.