© 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. 47893
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
    æĮĤåľ¨
    -0.10
    éķ°
    -0.09
    å±±åĮº
    -0.09
    çĶŁç´ł
    -0.09
    èµı
    -0.09
    æĮĤçĿĢ
    -0.08
    å¤ļæł·åĮĸ
    -0.08
    ãģªãĤĤãģ®
    -0.08
    wis
    -0.08
    inus
    -0.08
    POSITIVE LOGITS
    çªĿ
    0.09
    æĮ½æķij
    0.08
    æĮ½åĽŀ
    0.08
     Affero
    0.08
    æĺ¯æĪijçļĦ
    0.08
    aines
    0.08
    大家éĥ½
    0.08
    æ²»å®ī
    0.08
    chair
    0.08
     Nest
    0.08
    Activations Density 0.068%

    No Known Activations