© 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. 4551
    Prev
    Next
    INDEX
    Explanations

    immediate or short term

    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
    èĩªä»İ
    -0.09
    illion
    -0.09
    èĩªæľī
    -0.09
    æ¢ħèĬ±
    -0.09
    çļĦåľ°æŃ¥
    -0.09
    chan
    -0.08
    以å¾Ģ
    -0.08
    ç°Ł
    -0.08
    ally
    -0.08
    æ·±å¤Ħ
    -0.08
    POSITIVE LOGITS
     immediate
    0.18
    çľ¼åīį
    0.16
    åį³æŶ
    0.15
    çľ¼åīįçļĦ
    0.15
     Immediate
    0.15
    çŁŃæľŁåĨħ
    0.15
    çŁŃæľŁ
    0.14
    å½ĵä¸ĭ
    0.14
    ä¸ĢæŶ
    0.14
    Immediate
    0.14
    Activations Density 0.070%

    No Known Activations