© 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. 32-TRANSCODER-HP
    7. 42457
    Prev
    Next
    INDEX
    Explanations

    Proper nouns and names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ano
    -0.29
    BAL
    -0.27
    beiten
    -0.26
    Snippet
    -0.25
     Kong
    -0.24
     conclus
    -0.24
    íĶ¼
    -0.23
    æ·¼
    -0.23
    /GPL
    -0.23
    aso
    -0.23
    POSITIVE LOGITS
    主ä¹īæĢĿæĥ³
    0.26
    vh
    0.25
    ords
    0.25
     tứ
    0.25
    rang
    0.25
    orer
    0.24
    rad
    0.24
    .randrange
    0.24
    neh
    0.23
     Nev
    0.23
    Activations Density 0.001%

    No Known Activations