© 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. 4536
    Prev
    Next
    INDEX
    Explanations

    alone

    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
    佬
    -0.10
    ä¸Ńæľī
    -0.09
    ë°©
    -0.09
    HING
    -0.08
    dam
    -0.08
    ç®Ģ称
    -0.08
    ä¸ĩ家
    -0.08
    ol
    -0.08
    ound
    -0.08
    direct
    -0.08
    POSITIVE LOGITS
     baÅŁÄ±na
    0.12
    chars
    0.11
    æ´İ
    0.10
    æ¶İ
    0.10
    usz
    0.10
    SOLE
    0.09
     Rach
    0.09
    verständlich
    0.09
    czy
    0.09
    åIJĦ项
    0.09
    Activations Density 0.009%

    No Known Activations