© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 163131
    Prev
    Next
    INDEX
    Explanations

    names or code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bog
    -0.26
    æķ´åIJĪ
    -0.26
    äºĭä¸ļ
    -0.25
    fra
    -0.25
    éĴī
    -0.25
     Ã¶ÄŁ
    -0.25
    åħ¬å¼ĢæĭĽèģĺ
    -0.25
    é«ĺä»·
    -0.25
    é»ĺ
    -0.24
    æĢ§çļĦ
    -0.24
    POSITIVE LOGITS
     derivative
    0.27
    åŁİéĩĮ
    0.26
    è°
    0.26
    ìĹ¼
    0.26
    çľĭäºĨ
    0.25
    _derivative
    0.25
    ignal
    0.24
    heed
    0.24
    abajo
    0.24
     comply
    0.24
    Activations Density 0.014%

    No Known Activations