© 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. 52993
    Prev
    Next
    INDEX
    Explanations

    numbers and lists

    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
    ä¿©
    -0.10
    æģŃ
    -0.09
     dolayı
    -0.09
    å¤įæ´»
    -0.09
    ä¹ĭ称
    -0.09
    äºĶä¸Ģ
    -0.09
    roke
    -0.09
    ission
    -0.08
     Jame
    -0.08
     Kidd
    -0.08
    POSITIVE LOGITS
    atoi
    0.08
    缴èĩ³
    0.08
    /or
    0.08
    çĹŀ
    0.08
     etc
    0.08
    ãģ¨ãģĦãģ£ãģŁ
    0.08
    éĥ½éĿŀ常
    0.08
    /etc
    0.08
    以èĩ³äºİ
    0.08
    éĥ½å¾Ī
    0.08
    Activations Density 0.290%

    No Known Activations