© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52640
    Prev
    Next
    INDEX
    Explanations

    names followed by 's

    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
    _("
    -0.09
    è¶ħé«ĺ
    -0.09
    æ½
    -0.09
    åªļ
    -0.09
    åıijå±ķæĪĺçķ¥
    -0.09
    lifting
    -0.09
    _('
    -0.09
    æ°ijäºĭ
    -0.09
    çݯçIJĥ
    -0.09
    ç²¾å¯Ĩ
    -0.09
    POSITIVE LOGITS
    æĸ¯åĿ¦
    0.09
    æīĪ
    0.08
    isty
    0.08
    åŀ¢
    0.08
    ä¿ij
    0.08
    èļ±
    0.08
     mote
    0.08
    ç´łè´¨æķĻèĤ²
    0.08
     overd
    0.08
    alk
    0.07
    Activations Density 0.105%

    No Known Activations