© 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. 96083
    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
    åĮ¹éħį
    -0.35
    matching
    -0.32
    Matching
    -0.31
    urable
    -0.30
     matching
    -0.30
    _match
    -0.29
     pul
    -0.28
     matched
    -0.28
     Matching
    -0.28
    ä¹İ
    -0.28
    POSITIVE LOGITS
     riot
    0.29
    ä¸Ģæīĭ
    0.29
     elephant
    0.29
    æīĵåĵį
    0.28
    ives
    0.25
    å¢ŀåĬłåĢ¼
    0.25
    éħĮ
    0.25
     план
    0.24
    IVES
    0.24
    头çļ®
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.