© 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. 162536
    Prev
    Next
    INDEX
    Explanations

    web data and code, symbols

    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
    å¾Īå¿«
    -0.30
    EZ
    -0.29
    Brown
    -0.28
    Ky
    -0.26
    atron
    -0.26
    ,readonly
    -0.26
    consin
    -0.25
    å¾Ī好
    -0.25
     quickly
    -0.24
    åı¤éķĩ
    -0.24
    POSITIVE LOGITS
    éĵº
    0.31
    plug
    0.29
    åĽŀåĽ½
    0.28
    æ®Ĭ
    0.27
     UNESCO
    0.27
    çļĦèĥ½éĩı
    0.26
    缴è§Ĥ
    0.26
    è·¨åĽ½
    0.26
    çĵľ
    0.26
    æīĢ
    0.25
    Activations Density 0.011%

    No Known Activations