© 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. 17713
    Prev
    Next
    INDEX
    Explanations

    all

    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
    icker
    -0.11
    azer
    -0.09
    ä¸įæĪIJ
    -0.09
    è£ĺ
    -0.09
    (sig
    -0.09
    离
    -0.09
    ç§Ģ丽
    -0.09
    åı¤èĢģçļĦ
    -0.08
    çİĭçĪ·
    -0.08
    èĩªæķij
    -0.08
    POSITIVE LOGITS
    æģģ
    0.10
    igator
    0.10
    åħħ
    0.10
    ged
    0.09
    绣çŃ¹æİ¨è¿Ľ
    0.09
    å½ĵä¹ĭ
    0.08
    geme
    0.08
    STANCE
    0.08
    ra
    0.08
    ä¸ĢåĪ»
    0.08
    Activations Density 0.084%

    No Known Activations