© 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. 50238
    Prev
    Next
    INDEX
    Explanations

    not only... also

    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
    asl
    -0.08
    è´¢
    -0.08
    åģľçķĻåľ¨
    -0.08
    anes
    -0.08
    éĿŀ常çļĦ
    -0.08
     ë¶Ī구íķĺê³ł
    -0.08
    æĺ¯æ¯Ķè¾ĥ
    -0.08
    att
    -0.08
    upal
    -0.07
    mir
    -0.07
    POSITIVE LOGITS
     also
    0.38
    also
    0.33
     ÑĤакже
    0.33
     Also
    0.30
    Also
    0.29
     juga
    0.29
     também
    0.27
     cũng
    0.27
    ä¹Łè¦ģ
    0.27
    ä¹Łæľī
    0.27
    Activations Density 0.193%

    No Known Activations