© 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. 1254
    Prev
    Next
    INDEX
    Explanations

    go or throw story Copyright

    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
    æīĩ
    -0.10
    é¹°
    -0.09
    ExecutionContext
    -0.09
    å¤ļå±Ĥ次
    -0.09
    æĻ®
    -0.09
    _preview
    -0.08
    æݧ
    -0.08
    preview
    -0.08
     наблÑİ
    -0.08
    åĪĽ
    -0.08
    POSITIVE LOGITS
    å°±å¾Ĺ
    0.11
    ãģªãģijãĤĮãģ°
    0.11
    許
    0.10
    æŶæĬ¥
    0.10
    转åħ¥
    0.10
    许
    0.09
    讪
    0.09
    å¦Ĥæŀľä¸į
    0.09
    å¾Īå¿«å°±
    0.09
    åİ¿åħ¬å®īå±Ģ
    0.09
    Activations Density 0.039%

    No Known Activations