© 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. 10129
    Prev
    Next
    INDEX
    Explanations

    forms and variants

    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
    泫
    -0.11
    ä¸Ģåı£
    -0.10
    uron
    -0.09
    å¼Ģå§ĭäºĨ
    -0.09
    ILD
    -0.09
    éĶ£
    -0.08
    REW
    -0.08
    ä¸Ģç¢Ĺ
    -0.08
    åħĪè¿ĽæĬĢæľ¯
    -0.08
    楣
    -0.08
    POSITIVE LOGITS
    åıĺå¼Ĥ
    0.10
    variant
    0.10
     forms
    0.10
    _forms
    0.10
     variant
    0.10
    å²·
    0.10
    forms
    0.09
     variants
    0.09
    å·¨åŀĭ
    0.09
     ваÑĢианÑĤ
    0.09
    Activations Density 0.246%

    No Known Activations