© 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. 54254
    Prev
    Next
    INDEX
    Explanations

    showing a premiere

    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
    ervo
    -0.10
    Ñĩив
    -0.10
    ische
    -0.10
    tober
    -0.09
    oko
    -0.08
    åıŁ
    -0.08
    USED
    -0.08
    s
    -0.08
    åĩºåľº
    -0.08
    alia
    -0.08
    POSITIVE LOGITS
    è¿ĻæĶ¯
    0.10
    clé
    0.09
    centage
    0.09
    ichel
    0.09
    äºĨä¸Ģæī¹
    0.09
    éĹ®é¢ĺæĺ¯
    0.09
    è¦ģçŁ¥éģĵ
    0.09
    èĪįå¾Ĺ
    0.09
     aVar
    0.09
    iors
    0.09
    Activations Density 0.013%

    No Known Activations