© 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. 26855
    Prev
    Next
    INDEX
    Explanations

    in the case of

    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
    éģIJ
    -0.10
    稽
    -0.09
    åĨĻçļĦ
    -0.09
    åı£æ°´
    -0.09
    çĶ¨å¾®ä¿¡
    -0.08
    绿水éĿĴå±±
    -0.08
    快讯
    -0.08
    çĿ¢
    -0.08
    çĥŃçĤ¹
    -0.08
    模èĮĥ
    -0.08
    POSITIVE LOGITS
    wor
    0.11
    æĪij个人
    0.10
    æķ°çĽ®
    0.09
    _processors
    0.09
    tent
    0.09
     многиÑħ
    0.08
    身
    0.08
    éĤ£äºĽ
    0.08
    æŁIJäºĽ
    0.08
     жид
    0.08
    Activations Density 0.043%

    No Known Activations