© 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. 30233
    Prev
    Next
    INDEX
    Explanations

    BMW 1 Series Cars

    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
    满满çļĦ
    -0.10
    èĢģ人
    -0.09
    èĹľ
    -0.09
    è¿ŀ线
    -0.08
    åĦ¿
    -0.08
    äºĨä¸Ģ个
    -0.08
    ä½ķåĨµ
    -0.08
    潦
    -0.08
    身价
    -0.08
    äºĨ好å¤ļ
    -0.08
    POSITIVE LOGITS
    hé
    0.10
    ìłĪ
    0.09
    ç³»åĪĹ
    0.09
    ç³»åĪĹ产åĵģ
    0.09
    å®ļä»·
    0.08
    etto
    0.08
    ç¾
    0.08
    TickCount
    0.08
    antage
    0.08
    ç¾İ人
    0.08
    Activations Density 0.036%

    No Known Activations