© 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. 31-TRANSCODER-HP
    7. 19563
    Prev
    Next
    INDEX
    Explanations

    diabetes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    менÑĤ
    -0.30
    æĭ±
    -0.27
    íĤ¹
    -0.26
    ISE
    -0.25
     bình
    -0.25
    罩
    -0.25
    isen
    -0.25
    å°Ŀ
    -0.25
    寸
    -0.24
    éĩĩ纳
    -0.24
    POSITIVE LOGITS
     Di
    0.79
     di
    0.76
    Di
    0.75
    -di
    0.75
    _di
    0.71
    di
    0.68
    (di
    0.65
    .di
    0.60
     DI
    0.59
    迪
    0.57
    Activations Density 19.902%

    No Known Activations