© 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. 88151
    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
     mess
    -0.30
    unce
    -0.28
    ourced
    -0.27
     sourcing
    -0.26
    WithString
    -0.26
     lod
    -0.25
    ç½ķ
    -0.24
     loc
    -0.24
    каÑĢ
    -0.24
    æĭĹ
    -0.24
    POSITIVE LOGITS
     //</
    0.28
    ¹Ħ
    0.26
    éĹŃ
    0.25
    ready
    0.25
    ago
    0.25
     milan
    0.24
     READY
    0.24
    人æ°ijéĵ¶è¡Į
    0.24
    CFG
    0.24
    abbit
    0.24
    Activations Density 0.011%

    No Known Activations

    This feature has no known activations.