© 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. 163795
    Prev
    Next
    INDEX
    Explanations

    Matthew

    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
    çłĶ究éĻ¢
    -0.27
    inee
    -0.26
    éĴĵé±¼
    -0.24
     Cond
    -0.24
     Weekly
    -0.24
    ubyte
    -0.24
    Notify
    -0.24
    Ñĥл
    -0.24
     weekly
    -0.24
    :user
    -0.24
    POSITIVE LOGITS
    éĿ¢åIJij
    0.31
    .singleton
    0.27
    å±ķ示
    0.26
    æݨåĬ¨
    0.25
    å±ķçİ°
    0.25
    jang
    0.25
     sammen
    0.24
    anden
    0.24
    ä¸Ĭåįĥ
    0.24
    REFER
    0.23
    Activations Density 0.000%

    No Known Activations