© 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. 6896
    Prev
    Next
    INDEX
    Explanations

    ever something

    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
    èĩ»
    -0.09
    å¹³æŶ
    -0.08
    å½»
    -0.08
    综
    -0.08
    inki
    -0.08
    stab
    -0.08
    cles
    -0.08
     chances
    -0.08
    å½ĵåľ°
    -0.08
    atus
    -0.08
    POSITIVE LOGITS
    åħ±åĴĮåĽ½
    0.09
    æĦ¦
    0.09
    isu
    0.09
    æĪĸå°Ĩ
    0.09
    å¿łè¯ļ
    0.09
    æľīè¿ĩ
    0.09
    çļĦä½ľåĵģ
    0.09
    su
    0.08
    åı£åı·
    0.08
    çī¹éĤĢ
    0.08
    Activations Density 0.017%

    No Known Activations