© 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. 27-TRANSCODER-HP
    7. 9353
    Prev
    Next
    INDEX
    Explanations

    Kentucky and West Virginia

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¹¼ç¨ļ
    -0.26
    æĮ¥
    -0.25
    hana
    -0.25
    _schedule
    -0.25
    Schedule
    -0.24
     Schedule
    -0.24
    ä½ľæģ¯
    -0.24
    ih
    -0.24
    umas
    -0.24
     ipsum
    -0.23
    POSITIVE LOGITS
    qus
    0.30
    ÅĤam
    0.27
    quets
    0.27
    é¹ĥ
    0.26
    çľģéĴ±
    0.25
    alic
    0.25
     Tea
    0.24
    åįģå¹´åīį
    0.24
    åĹ½
    0.24
    å¾·å·ŀ
    0.24
    Activations Density 0.012%

    No Known Activations