© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 63307
    Prev
    Next
    INDEX
    Explanations

    similarity and hypothetical situations

    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
    å§Ĺ
    -0.09
    建çŃijå¸Ī
    -0.08
    .communic
    -0.08
    鸡汤
    -0.08
    пп
    -0.08
    بت
    -0.08
    èĩ³æѤ
    -0.08
    å¥ķ
    -0.08
     WOW
    -0.08
    ยาย
    -0.08
    POSITIVE LOGITS
    俺
    0.13
    åĴ±ä»¬
    0.13
    åĴ±
    0.12
    为åķ¥
    0.12
     gonna
    0.12
    åķ¥
    0.11
    èĢģåŃIJ
    0.10
     gotta
    0.09
     kinda
    0.09
    ãģĺãĤĥ
    0.09
    Activations Density 0.124%

    No Known Activations