© 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. 56726
    Prev
    Next
    INDEX
    Explanations

    adverse effects

    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
    ä¸įæŃ¢
    -0.11
     Ñģка
    -0.10
    imate
    -0.10
    æ³ł
    -0.10
    对æĬĹ
    -0.10
    èĶļ
    -0.10
    åľ¬
    -0.09
    以èī²
    -0.09
    æĬĢå¸Ī
    -0.09
    ãģ¤ãģĦ
    -0.09
    POSITIVE LOGITS
    åIJİæŀľ
    0.10
     effects
    0.09
    lyph
    0.09
    oir
    0.08
    chin
    0.08
    çļĦå½±åĵį
    0.08
    ç»ıæµİ社ä¼ļ
    0.08
    è´ŁéĿ¢å½±åĵį
    0.08
    -effects
    0.08
    çªģ
    0.08
    Activations Density 0.070%

    No Known Activations