© 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. 163422
    Prev
    Next
    INDEX
    Explanations

    underground

    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
    upro
    -0.27
    é»Ħèī²
    -0.26
    fieldset
    -0.25
    ä¸Ģå¤ľ
    -0.25
    交
    -0.25
    æ¯ı天
    -0.25
    京
    -0.24
    æ¯ıæĹ¥
    -0.24
     yellow
    -0.24
     sais
    -0.24
    POSITIVE LOGITS
    ivating
    0.27
    shops
    0.25
    _dense
    0.25
    maze
    0.24
    ByExample
    0.24
    èĽ¾
    0.24
    åĩºçİ°åľ¨
    0.24
    éĩįæķ´
    0.24
    éĻ¤æѤ
    0.24
    举æݪ
    0.24
    Activations Density 0.007%

    No Known Activations