© 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. 20288
    Prev
    Next
    INDEX
    Explanations

    breeders or growers

    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
    ry
    -0.09
    emonic
    -0.09
    jon
    -0.09
    âĺŀ
    -0.09
    åıijå±ķ空éĹ´
    -0.09
    asting
    -0.08
    wit
    -0.08
     ary
    -0.08
    ÙĦس
    -0.08
    .setPrototypeOf
    -0.08
    POSITIVE LOGITS
    mpp
    0.09
    éĺ¿å§¨
    0.09
    eras
    0.09
    pecific
    0.08
    weet
    0.08
    认è¯Ĩ
    0.08
    aat
    0.08
     GRAT
    0.08
    OrUpdate
    0.08
     ult
    0.08
    Activations Density 0.004%

    No Known Activations