© 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. 163821
    Prev
    Next
    INDEX
    Explanations

    Then

    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
    iphery
    -0.25
    èĹı
    -0.25
    gettext
    -0.24
    /people
    -0.24
    ducted
    -0.24
    çī¹çĤ¹æĺ¯
    -0.24
    æľ¬èº«çļĦ
    -0.24
    主義
    -0.23
    istics
    -0.23
    poses
    -0.23
    POSITIVE LOGITS
    ,
    0.35
    ç´§æİ¥çĿĢ
    0.30
     however
    0.27
    then
    0.27
    æİ¥çĿĢ
    0.27
    ï¼Į
    0.27
    ,...
    0.27
    ament
    0.25
    ,',
    0.25
    ï¼Įåľ¨
    0.25
    Activations Density 0.040%

    No Known Activations