© 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. 53505
    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
    æľīç§į
    -0.09
    èģĶç½ij
    -0.09
    åį³å°ĨåĪ°æĿ¥
    -0.09
    vero
    -0.08
    å¾ģæ±Ĥ
    -0.08
    çıŃåŃIJæĪIJåijĺ
    -0.08
    å®Ľ
    -0.08
    åłĤ
    -0.08
    å¤ļä½ĻçļĦ
    -0.08
    楼主
    -0.08
    POSITIVE LOGITS
     alone
    0.25
    alone
    0.21
     Alone
    0.19
    ä¹ŁæĹłæ³ķ
    0.15
    ãģłãģijãģ§
    0.14
     saja
    0.14
    æīĢèĥ½
    0.14
    并ä¸įèĥ½
    0.14
    ä¹Łä¸įåı¯èĥ½
    0.14
    -alone
    0.13
    Activations Density 0.315%

    No Known Activations