© 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. 35834
    Prev
    Next
    INDEX
    Explanations

    label attribute

    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
    0
    -0.09
    åıĹçIJĨ
    -0.08
    6
    -0.08
    ä¹±
    -0.08
    å¡ĺ
    -0.08
    4
    -0.08
    1
    -0.08
    8
    -0.08
    .asp
    -0.08
    blem
    -0.08
    POSITIVE LOGITS
    æ¯Ķä¾ĭ
    0.11
    å¥ł
    0.11
    åĬ¨éĿĻ
    0.11
    áĥ«
    0.10
    åįłæ¯Ķ
    0.09
    åĺ£
    0.09
    踵
    0.09
    çİĭåħĪçĶŁ
    0.09
    occo
    0.09
    æĻºåķĨ
    0.09
    Activations Density 0.036%

    No Known Activations