© 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. 26926
    Prev
    Next
    INDEX
    Explanations

    yet or but

    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
    è´
    -0.09
    ä¸įä»ħè¦ģ
    -0.08
    rams
    -0.08
     crop
    -0.08
    ä¼Ł
    -0.08
    ram
    -0.08
    ä½ľçī©
    -0.08
    åħĪ
    -0.08
    åħĪè¡Į
    -0.08
    gb
    -0.08
    POSITIVE LOGITS
    ä¸į失
    0.15
    ä¸įèĩ³äºİ
    0.13
    åıĪæľī
    0.13
    åıĪèĥ½
    0.13
    ä¸įå¿ĺ
    0.11
    åıĪè¦ģ
    0.11
    åıĪ被
    0.10
    ä¿ĿæĮģçĿĢ
    0.10
    åıĪ
    0.10
    ä¸İæѤåIJĮæŶ
    0.10
    Activations Density 0.072%

    No Known Activations