© 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. 18520
    Prev
    Next
    INDEX
    Explanations

    horns, unicorn, tusks

    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
    bol
    -0.09
    室
    -0.08
    åŃ
    -0.08
    èĭŁ
    -0.08
    anke
    -0.08
    pper
    -0.08
    æ¸Ĭ
    -0.08
    ÙĦØ©
    -0.08
    anel
    -0.08
    æ¹
    -0.08
    POSITIVE LOGITS
    çĭ¬è§Ĵ
    0.14
     horns
    0.12
    çĬĦ
    0.11
     horn
    0.11
     unicorn
    0.10
     tus
    0.10
    éĿŀåĩ¡
    0.10
    èĹIJ
    0.09
     ung
    0.09
    å´ĸ
    0.09
    Activations Density 0.038%

    No Known Activations