© 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. 7587
    Prev
    Next
    INDEX
    Explanations

    English summary

    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
    æ³ĵ
    -0.10
    comed
    -0.09
    ashes
    -0.08
     fly
    -0.08
     traf
    -0.08
     Fly
    -0.08
     COMPUT
    -0.08
    eman
    -0.08
    æĬĹ
    -0.08
    å®Ī
    -0.08
    POSITIVE LOGITS
    åı¶çīĩ
    0.10
    åı¶
    0.09
    idis
    0.09
    åĸľ
    0.09
    æļĤåģľ
    0.09
    åĶĨ
    0.09
    æĶ¶ç¼©
    0.09
    _CF
    0.09
    pig
    0.09
    篾
    0.09
    Activations Density 0.092%

    No Known Activations