© 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. 23014
    Prev
    Next
    INDEX
    Explanations

    itself

    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
    缴æݥ影åĵį
    -0.09
    éĻ¤æѤ
    -0.09
    åľ¨å¸Ĥåľºä¸Ĭ
    -0.09
    ä½ľæģ¯
    -0.09
    à¸Ĺรà¸ĩ
    -0.09
     nghiá»ĩp
    -0.09
    åĩºå¢ĥ
    -0.08
     Ñģвоем
    -0.08
    çĻ½çĻ½
    -0.08
     онлайн
    -0.08
    POSITIVE LOGITS
    ä¹Łæĺ¯ä¸Ģ个
    0.10
    è¿ĺæĺ¯æ¯Ķè¾ĥ
    0.10
    å°±æĺ¯ä¸Ģ个
    0.10
    çĩĥ
    0.09
     Cath
    0.09
    éĤ£ä¹Īç®Ģåįķ
    0.09
    ridge
    0.09
    aret
    0.08
    å§ļ
    0.08
    zelf
    0.08
    Activations Density 0.020%

    No Known Activations