© 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. 61348
    Prev
    Next
    INDEX
    Explanations

    making visible

    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
     Gil
    -0.09
    finished
    -0.08
    éľľ
    -0.08
    æĥ³è¿ĩ
    -0.08
    æŃ¢
    -0.08
    è¿ĩå¤ļ
    -0.08
     puzzle
    -0.08
    æĪijçĽ¸ä¿¡
    -0.08
    æİĪæĿĥ
    -0.08
    åģ·åģ·
    -0.07
    POSITIVE LOGITS
    æļ´éľ²
    0.15
    åıijçİ°äºĨ
    0.14
    æīįåıijçİ°
    0.14
    æĺ¾çİ°
    0.13
    åĩ¸æĺ¾
    0.13
    åİŁåħĪ
    0.13
    æĺ¾éľ²
    0.13
    æıŃ示
    0.12
    åİŁæĿ¥
    0.12
    æĶ¾å¤§
    0.12
    Activations Density 0.108%

    No Known Activations