© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6787
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    okes
    -0.29
    èĢĮæĺ¯
    -0.28
    æ¸ħæ´Ĺ
    -0.26
    ç¼
    -0.26
    ä½Ĩå®ŀéĻħä¸Ĭ
    -0.26
    çĵ¶
    -0.25
    河水
    -0.25
     owed
    -0.25
    oked
    -0.25
     spread
    -0.25
    POSITIVE LOGITS
    .lv
    0.31
    ÑĮе
    0.27
    ymbol
    0.27
    éĩĮç¨ĭç¢ij
    0.25
    essim
    0.24
    ASTE
    0.24
    ojis
    0.24
    üp
    0.24
     Plum
    0.24
    ild
    0.23
    Activations Density 0.028%

    No Known Activations

    This feature has no known activations.