© 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. 51327
    Prev
    Next
    INDEX
    Explanations

    must find

    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
    orry
    -0.10
    ARAM
    -0.09
     Chew
    -0.09
    oger
    -0.09
    è±ī
    -0.08
    Ok
    -0.08
     furn
    -0.08
     consideration
    -0.08
    ighth
    -0.08
    æ±²
    -0.08
    POSITIVE LOGITS
    åħ®
    0.11
    åĴ±
    0.10
    ä¹ĭæīĢ
    0.10
    æģģ
    0.09
    åıĤ
    0.09
    åĿ
    0.09
    亲人
    0.09
    æĺ¯æĪij
    0.09
    亲çĪ±
    0.09
     gonna
    0.08
    Activations Density 0.202%

    No Known Activations