© 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. 19480
    Prev
    Next
    INDEX
    Explanations

    take advantage of

    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
    FromClass
    -0.11
    åįĵ
    -0.11
    OutOfBounds
    -0.10
    éĿłçĿĢ
    -0.10
    Tho
    -0.10
    _ENCOD
    -0.10
    æķ´é½IJ
    -0.10
    åIJĪãģĨ
    -0.09
    elts
    -0.09
    CppClass
    -0.09
    POSITIVE LOGITS
    广éĺĶçļĦ
    0.12
    å¥ijæľº
    0.09
     opportunities
    0.09
     allowed
    0.09
    广éĺĶ
    0.08
    æ³®
    0.08
     opportunity
    0.08
    7
    0.08
    2
    0.08
     situation
    0.08
    Activations Density 0.039%

    No Known Activations