© 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. 35-TRANSCODER-HP
    7. 39741
    Prev
    Next
    INDEX
    Explanations

    Weather and temperature

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     the
    -0.36
     weather
    -0.31
    weather
    -0.30
    the
    -0.29
    Weather
    -0.29
     a
    -0.28
    â»
    -0.28
     temperatures
    -0.28
    天æ°Ķ
    -0.27
    counts
    -0.26
    POSITIVE LOGITS
    ä½Ļ家
    0.26
     pies
    0.26
    æĿ¥æī¾
    0.26
    -present
    0.25
     blobs
    0.25
    -prop
    0.25
     spiders
    0.24
     trailers
    0.24
    -but
    0.24
    /lg
    0.24
    Activations Density 1.575%

    No Known Activations