© 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. 56926
    Prev
    Next
    INDEX
    Explanations

    working together, collaborating

    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
     heroic
    -0.09
     Beitrag
    -0.09
    çĹħ
    -0.08
    æĪ·åı£
    -0.08
    elig
    -0.08
    TÄ°
    -0.08
    è¿ĩ度
    -0.08
    说åĩº
    -0.08
    ỡ
    -0.08
    çĸ
    -0.08
    POSITIVE LOGITS
    é»ĺå¥ij
    0.12
    æ¸Ĭ
    0.11
    èĤĥ
    0.10
    亲å¯Ĩ
    0.10
    æIJŃæ¡£
    0.10
    ç´§å¯Ĩ
    0.09
    ä¼Ļä¼´
    0.09
    éĩįç»Ħ
    0.09
    ette
    0.09
    åı¦
    0.08
    Activations Density 0.052%

    No Known Activations