© 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. 62496
    Prev
    Next
    INDEX
    Explanations

    months of the year

    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
    çĵľ
    -0.08
    çĸ³
    -0.08
    æĤłæĤł
    -0.08
    åĨ¬åŃ£
    -0.08
    åѦåijĺ
    -0.08
    Ñĩив
    -0.08
    igt
    -0.08
    stakes
    -0.08
     окол
    -0.08
     cig
    -0.08
    POSITIVE LOGITS
    å°ijè§ģ
    0.10
    æĹłæ¯Ķ
    0.10
    éĿ¢è²Į
    0.09
    éĥ½éĿŀ常
    0.09
    æľīæľŁ
    0.09
    åľ¨åħ¨åĽ½
    0.08
    losion
    0.08
    个åĪ«
    0.08
    çĺ«
    0.08
    æŀ¶
    0.08
    Activations Density 0.139%

    No Known Activations