© 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. 27755
    Prev
    Next
    INDEX
    Explanations

    email address

    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¨åī¯
    -0.10
     Äijòi
    -0.10
    ugi
    -0.09
    ela
    -0.09
    iny
    -0.08
     Hóa
    -0.08
    ibri
    -0.08
    åĪĩåħ¥çĤ¹
    -0.08
    ajan
    -0.08
    éĢĤåIJĪèĩªå·±
    -0.08
    POSITIVE LOGITS
    æĶ¶åıĸ
    0.09
    åĨľçĶ°
    0.09
    满äºĨ
    0.09
    éĤ®ç®±
    0.09
     emailAddress
    0.09
    mailto
    0.09
    åĹ·
    0.09
    èģĶç³»
    0.08
    è¥Ł
    0.08
     поÑĩ
    0.08
    Activations Density 0.093%

    No Known Activations