© 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. 98827
    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
    ility
    -0.27
    容
    -0.25
    anker
    -0.24
    ILITY
    -0.24
    LOC
    -0.23
    Loc
    -0.23
     loosen
    -0.23
     pack
    -0.23
     loc
    -0.23
     Prof
    -0.23
    POSITIVE LOGITS
    ç»ĻæĤ¨
    0.22
     Vid
    0.22
     hã
    0.22
     yourselves
    0.22
    ìķ±
    0.21
     domestically
    0.21
    å½ĵæĪij
    0.21
    é¬ĥ
    0.21
     lineno
    0.21
     ringing
    0.21
    Activations Density 0.027%

    No Known Activations

    This feature has no known activations.