© 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. 33292
    Prev
    Next
    INDEX
    Explanations

    anyone or anybody asking

    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
    çŀĢ
    -0.09
    çİ°çĬ¶
    -0.09
    离ä¸įå¼Ģ
    -0.09
    å°±æĺ¯è¿Ļæł·
    -0.08
    å¦Ĥæŀľæ²¡æľī
    -0.08
     dru
    -0.08
    åıijè´¢
    -0.08
     apparently
    -0.08
    1
    -0.08
    æĹĥ
    -0.08
    POSITIVE LOGITS
    eft
    0.11
    æľīä»»ä½ķ
    0.11
    ãģŀ
    0.10
    éĹ®æĪij
    0.10
    åĿĬ
    0.10
    IZER
    0.09
    eq
    0.09
    åį¿
    0.09
    å¯Ŀ
    0.09
    è¢Ĵ
    0.09
    Activations Density 0.010%

    No Known Activations