© 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. 61862
    Prev
    Next
    INDEX
    Explanations

    instinct intuition sense perception

    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
    éĹª
    -0.09
    è·¨
    -0.09
    å®
    -0.08
    éĹªçĥģ
    -0.08
     Nir
    -0.08
    åħĪè¿Ľ
    -0.08
    ç«ĻçĤ¹
    -0.08
     bé
    -0.08
     imp
    -0.08
     teg
    -0.08
    POSITIVE LOGITS
    æķıéĶIJ
    0.15
    æķıæĦŁ
    0.13
    çģµæķı
    0.13
    æĬĬæı¡
    0.13
     intuition
    0.12
    çļĦæĦŁè§ī
    0.12
     instincts
    0.11
    çģµæ°Ķ
    0.11
    åĪ¤æĸŃ
    0.11
     sense
    0.11
    Activations Density 0.034%

    No Known Activations