© 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. 96185
    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
    åı¯æĢľ
    -0.27
    äºĨä¸Ģåı£
    -0.26
    @student
    -0.26
    cluding
    -0.25
    ç¿»
    -0.25
    itur
    -0.25
    iciones
    -0.25
     dice
    -0.25
    ÙĬÙĥا
    -0.24
    qual
    -0.24
    POSITIVE LOGITS
    ç«Ł
    0.32
    èŀį
    0.27
    ernes
    0.27
    logan
    0.26
    çļĦä¸ĢéĿ¢
    0.26
     ứng
    0.26
    stoff
    0.26
    éĩĬ
    0.25
     inflate
    0.24
    æ¼Ķ
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.