© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 26089
    Prev
    Next
    INDEX
    Explanations

    asking how

    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
    Negative Logits
    å·²ä¹ħ
    -0.10
    佬
    -0.10
    禧
    -0.08
    èĪĶ
    -0.08
     funny
    -0.08
    çĤ¹æ»´
    -0.08
    å¼ĭ
    -0.08
     til
    -0.08
    éľį
    -0.08
    ä¸įä½Ĩ
    -0.08
    POSITIVE LOGITS
    éĤ£ä»½
    0.10
    åıijå±ķéĺ¶æ®µ
    0.10
    Fri
    0.09
    æ´»è·ĥ
    0.09
    iggins
    0.09
    Tue
    0.09
    -cond
    0.09
    ÙĴ
    0.09
    寺
    0.09
    OwnProperty
    0.09
    Activations Density 0.005%

    No Known Activations