© 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. 6625
    Prev
    Next
    INDEX
    Explanations

    building enclosure or envelope

    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
    overn
    -0.09
    åĨ³
    -0.09
    æĻ¦
    -0.08
    çĿ¹
    -0.08
    ç«ĭå¿Ĺ
    -0.08
    orny
    -0.08
    itime
    -0.08
     полÑĥÑĩа
    -0.08
    Toolkit
    -0.08
    ç¥ļ
    -0.08
    POSITIVE LOGITS
    æįĭ
    0.10
    è½½ä½ĵ
    0.10
    åıĸ代
    0.10
    éĤĹ
    0.09
    éĢĢè¿ĺ
    0.09
    大éģĵ
    0.09
    lectic
    0.09
     Beau
    0.09
    å¹»
    0.09
    éºĴ
    0.09
    Activations Density 0.033%

    No Known Activations