© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38689
    Prev
    Next
    INDEX
    Explanations

    center or centre names

    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
    çī©çIJĨåѦ
    -0.09
    丰满
    -0.09
    èı±
    -0.09
    èĻIJ
    -0.09
    éĢļçķħ
    -0.09
    onga
    -0.08
    ays
    -0.08
    çŃł
    -0.08
    åŃ¦å®¶
    -0.08
    åħ¥åĽŃ
    -0.08
    POSITIVE LOGITS
    大大
    0.10
     Patt
    0.09
    æĻº
    0.09
    æĹłæīĢè°ĵ
    0.09
    æĪij们éĥ½
    0.09
    æķ²
    0.08
     ìľ
    0.08
    ogue
    0.08
    åħ´å¥ĭ
    0.08
    arra
    0.08
    Activations Density 0.020%

    No Known Activations