© 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. 53457
    Prev
    Next
    INDEX
    Explanations

    makes claims or allegations

    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
    äºĨ解åĪ°
    -0.09
    å«ģ
    -0.09
    æĻ¯
    -0.08
    墨
    -0.08
    饶
    -0.08
     unfolded
    -0.08
    ç»ļ丽
    -0.08
     absorb
    -0.08
    æľĢçĪ±
    -0.08
    æľīä¿¡å¿ĥ
    -0.08
    POSITIVE LOGITS
    cul
    0.09
     Goth
    0.09
    å¹Ķ
    0.09
    aben
    0.09
    è´¦
    0.08
    åĵ©
    0.08
    软件
    0.08
    åľ¨æ¸¸æĪıä¸Ń
    0.08
    ILED
    0.08
    iled
    0.08
    Activations Density 0.066%

    No Known Activations