© 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. 10373
    Prev
    Next
    INDEX
    Explanations

    personal information and data

    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
    西路
    -0.09
    éĵŃè®°
    -0.09
    unik
    -0.09
     wÅĤaÅĽnie
    -0.09
    å¾ģ
    -0.09
    æ¯ĶåĪ©
    -0.09
    ä¸ľè·¯
    -0.08
    igner
    -0.08
    lesen
    -0.08
    pps
    -0.08
    POSITIVE LOGITS
    łéĻ¤
    0.09
    èĪį
    0.09
    çĨ
    0.09
    ially
    0.08
     dir
    0.08
    æIJĶ
    0.08
    apos
    0.08
    æĭī
    0.08
     XC
    0.08
     continent
    0.08
    Activations Density 0.012%

    No Known Activations