© 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. 11630
    Prev
    Next
    INDEX
    Explanations

    from a to

    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
    黾
    -0.10
    ebin
    -0.10
    æ°Ķæ°Ľ
    -0.10
    uum
    -0.09
    éĥ¨ä¸»ä»»
    -0.09
    å°ıçĶ·åŃ©
    -0.09
    è¿Ľä¸ĢæŃ¥
    -0.09
    ç»Į
    -0.09
    æ²±
    -0.08
    åĽ½å®ī
    -0.08
    POSITIVE LOGITS
    åį¸
    0.09
    pling
    0.08
     Points
    0.08
    èľķ
    0.08
    çĤ¹
    0.08
    èĦij
    0.08
    åĽĬ
    0.08
    ÃŃn
    0.08
    arith
    0.07
    ount
    0.07
    Activations Density 0.093%

    No Known Activations