© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 108094
    Prev
    Next
    INDEX
    Explanations

    non-English text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ï¼ĮåĪĻ
    -0.34
    ï¼Įåľ¨
    -0.30
    !,↵
    -0.28
    دÙĪا
    -0.27
    (),↵↵
    -0.27
    .netflix
    -0.26
    ãĢij,
    -0.25
    ap
    -0.25
    ä¸įåĬ¨
    -0.25
    éħ¬
    -0.25
    POSITIVE LOGITS
    èģ¯
    0.26
    æ²»çĻĤ
    0.25
    并å°Ĩ
    0.24
    ugins
    0.24
    .ru
    0.23
    .Cos
    0.23
    ä¹Łä¸įæķ¢
    0.23
     Crescent
    0.23
    olis
    0.23
    ãĢģ
    0.23
    Activations Density 1.495%

    No Known Activations