© 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. 33-TRANSCODER-HP
    7. 53988
    Prev
    Next
    INDEX
    Explanations

    environment and climate

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Welt
    -0.29
    Tp
    -0.26
    /world
    -0.26
     Plat
    -0.26
    ä¸ĵåįĸ
    -0.25
    ptides
    -0.24
    ä¸ĸä¸Ĭ
    -0.24
    çļĦç²¾ç¥ŀ
    -0.23
    Fine
    -0.23
     orm
    -0.23
    POSITIVE LOGITS
     nature
    0.41
    nature
    0.35
     hum
    0.33
    Mother
    0.31
     offset
    0.29
    offset
    0.28
    Nature
    0.28
    æĢ§è´¨
    0.28
     man
    0.28
     Mother
    0.27
    Activations Density 0.021%

    No Known Activations