© 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. 30-TRANSCODER-HP
    7. 96546
    Prev
    Next
    INDEX
    Explanations

    grades

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erge
    -0.25
    å¼Ģå¹ķ
    -0.25
    velle
    -0.25
    ICODE
    -0.24
    æī§æ³ķ人åijĺ
    -0.24
    æĴĤ
    -0.24
     Gew
    -0.24
    寸
    -0.23
    车åİ¢
    -0.23
    .OPEN
    -0.23
    POSITIVE LOGITS
    çĤ¹
    0.47
     point
    0.42
     points
    0.42
    points
    0.39
    Points
    0.36
    -points
    0.36
    Point
    0.36
     Points
    0.35
    é»ŀ
    0.35
    point
    0.35
    Activations Density 0.890%

    No Known Activations