© 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. 62136
    Prev
    Next
    INDEX
    Explanations

    used for

    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
    çĬĬ
    -0.10
    ä¹Łèĥ½
    -0.10
    åħļå·¥å§Ķ
    -0.09
    éļIJ约
    -0.09
    驺
    -0.09
    æ´ĭ
    -0.09
    积水
    -0.08
    æµģæ°´
    -0.08
    bur
    -0.08
    .da
    -0.08
    POSITIVE LOGITS
    çĶ¨æĿ¥
    0.14
    å¹²åĺĽ
    0.11
    ä»Ģä¹Īåij¢
    0.10
    æĺ¯çĶ¨æĿ¥
    0.10
     purposes
    0.10
    éĺ²æŃ¢
    0.09
    究竣
    0.09
     regress
    0.08
    è´¯
    0.08
    çĶ¨äºİ
    0.08
    Activations Density 0.139%

    No Known Activations