© 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. 62459
    Prev
    Next
    INDEX
    Explanations

    iosync, Williams may, long-term

    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
    éĥ¨å§Ķ
    -0.10
     Copp
    -0.09
    VERR
    -0.09
     Beard
    -0.08
    大éĩı
    -0.08
     wed
    -0.08
    ildo
    -0.08
    åĽ¿
    -0.08
    illus
    -0.08
    baugh
    -0.08
    POSITIVE LOGITS
    çĽijæĬ¤
    0.09
    ä¹Ķæ²»
    0.09
    cip
    0.09
    пÑĥ
    0.09
    å²ģæľĪ
    0.09
    éĻĦå±ŀ
    0.09
    èĥ¸åı£
    0.09
    rot
    0.09
    pollo
    0.08
    ers
    0.08
    Activations Density 0.002%

    No Known Activations