© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 12069
    Prev
    Next
    INDEX
    Explanations

    at one point

    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
    eger
    -0.10
    缮åīį
    -0.09
    å½ĵåīįä½įç½®
    -0.09
    缮åīįåĽ½åĨħ
    -0.08
    erge
    -0.08
    缮åīįå·²
    -0.08
    äºĶæĺŁ
    -0.08
    è¡£
    -0.08
    contexts
    -0.08
    uje
    -0.08
    POSITIVE LOGITS
    ä¸Ģ度
    0.12
    说è¿ĩ
    0.10
    ikt
    0.09
    秽
    0.09
    çĴĥ
    0.09
    addir
    0.09
    被èªī为
    0.08
    好åĩłä¸ª
    0.08
    thora
    0.08
    æĽ¾
    0.08
    Activations Density 0.016%

    No Known Activations