© 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. 27822
    Prev
    Next
    INDEX
    Explanations

    which followed by words like any

    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
    -Origin
    -0.11
    inas
    -0.11
    èĸ¤
    -0.10
    æļ
    -0.10
    çŁ¥éģĵäºĨ
    -0.10
    ãĥªãĥ³ãĤ°
    -0.09
    èį
    -0.09
    å¿ĥ缮ä¸Ń
    -0.09
    anness
    -0.09
    issant
    -0.09
    POSITIVE LOGITS
    ich
    0.09
    igo
    0.09
     ÑģобÑģÑĤвенно
    0.08
    èµĦ
    0.08
    ç»Ļèĩªå·±
    0.08
     dear
    0.08
    onymous
    0.08
    亲çĪ±çļĦ
    0.07
    otor
    0.07
    ç»Ļä»ĸ
    0.07
    Activations Density 0.484%

    No Known Activations