© 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. 49902
    Prev
    Next
    INDEX
    Explanations

    sometimes with deadly results

    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
    mage
    -0.09
    åĬ«
    -0.09
    ENTITY
    -0.09
    LER
    -0.08
    indrical
    -0.08
    对äºİæĪij们
    -0.08
    åį°
    -0.08
    ady
    -0.08
    åĿļ强
    -0.08
    enos
    -0.08
    POSITIVE LOGITS
    åij
    0.09
    人éĥ½
    0.09
    ä¸į失
    0.08
    ester
    0.08
    æľįåĬ¡ä½ĵç³»
    0.08
    Multiplicity
    0.08
    inan
    0.07
    æī¿æİ¥
    0.07
    å¾ģæ±Ĥ
    0.07
    ä¸įä¹ı
    0.07
    Activations Density 0.120%

    No Known Activations