© 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. 24281
    Prev
    Next
    INDEX
    Explanations

    broadcast media

    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
    ourt
    -0.10
    ESCO
    -0.09
    è¡£çī©
    -0.09
    LEX
    -0.09
    ynth
    -0.09
    åĽ¾æłĩ
    -0.08
    _FATAL
    -0.08
    è½®å»ĵ
    -0.08
     Gors
    -0.08
    çĻ¾ç§ij
    -0.08
    POSITIVE LOGITS
    æĴŃåĩº
    0.11
    åıijè¡Į
    0.10
    é¦Ī
    0.09
    æĬķæĶ¾
    0.09
    央
    0.09
    åıijæĶ¾
    0.09
    æĶ¾æĺł
    0.09
    æĴŃæĶ¾
    0.09
     sheer
    0.09
    æµģä¼ł
    0.09
    Activations Density 0.320%

    No Known Activations