© 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. 30-TRANSCODER-HP
    7. 96602
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ",__
    -0.32
    ĵĺ
    -0.28
    è¿ģ
    -0.27
    ðŁijĪ
    -0.27
    -kit
    -0.25
    ihan
    -0.24
    ificate
    -0.24
     managed
    -0.23
    kits
    -0.23
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.23
    POSITIVE LOGITS
     lust
    0.29
    raid
    0.26
    lust
    0.26
    inet
    0.26
     деÑıÑĤелÑĮ
    0.26
    elling
    0.26
    USE
    0.25
    ÃĻ
    0.25
    æľīæĦı
    0.25
    æ·±æĥħ
    0.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.