© 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. 2439
    Prev
    Next
    INDEX
    Explanations

    First Amendment rights

    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
    赦
    -0.12
    åĶĩ
    -0.11
    代çIJĨ人
    -0.11
    å°±è¶Ĭ
    -0.10
    è¶Ĭ好
    -0.09
    çŁ³æ¦´
    -0.09
    zier
    -0.09
    éºĪ
    -0.09
     gar
    -0.09
    æµ·çĽĹ
    -0.09
    POSITIVE LOGITS
    åħ¬çĶ¨
    0.11
    äºĭä¸ļ
    0.09
    .tc
    0.09
    ehen
    0.08
     dá»±ng
    0.08
    orst
    0.08
    å¯ĵ
    0.08
    å«Į
    0.08
    inia
    0.08
    Ä»
    0.08
    Activations Density 0.050%

    No Known Activations