© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50574
    Prev
    Next
    INDEX
    Explanations

    degrees Celsius or C

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ematic
    -0.09
    ç½ij约
    -0.09
    åħ±é¸£
    -0.09
    ENA
    -0.08
    è°į
    -0.08
     Ont
    -0.08
    çĻ½éĵ¶
    -0.08
    RARY
    -0.08
    culate
    -0.08
    hip
    -0.08
    POSITIVE LOGITS
     Celsius
    0.10
    ibus
    0.10
    oram
    0.10
    æģª
    0.09
    inea
    0.09
    æĸ¹ä½į
    0.09
     pragma
    0.09
    court
    0.09
    geh
    0.09
    afone
    0.09
    Activations Density 0.014%

    No Known Activations