© 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. 163831
    Prev
    Next
    INDEX
    Explanations

    scientific/legal texts

    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
    ignite
    -0.26
    æŁ±
    -0.25
    ä¸įåı¯
    -0.25
    积æŀģåıĤä¸İ
    -0.25
    æĮĩ导
    -0.25
    æĢł
    -0.25
    ouns
    -0.24
    åı°æ¹¾
    -0.24
    æĸ¥
    -0.24
    å°Ĩåľ¨
    -0.24
    POSITIVE LOGITS
    纪å½ķ
    0.28
     profession
    0.28
     professions
    0.27
     tran
    0.26
     langu
    0.25
    lernen
    0.25
    atel
    0.25
    geb
    0.24
    éħ¿
    0.24
    è§Ĥæµĭ
    0.24
    Activations Density 0.001%

    No Known Activations