© 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. 52390
    Prev
    Next
    INDEX
    Explanations

    states of being and consciousness

    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
    acist
    -0.08
    hn
    -0.08
    å¼łæī¬
    -0.08
    ARTH
    -0.08
    举åĮĹ
    -0.07
    estre
    -0.07
    _ACTIV
    -0.07
    æĺİæĹ¥
    -0.07
    åĸĦ
    -0.07
    ä¸ī级
    -0.07
    POSITIVE LOGITS
    çĶŁåij½çļĦ
    0.10
    æ¹Ľ
    0.10
    èĪŀ
    0.09
    èĢĥä¸Ĭ
    0.09
    躯
    0.09
    æīįæĺ¯
    0.09
    æĹłæ¯Ķ
    0.09
    溥
    0.09
    egot
    0.09
    è°
    0.09
    Activations Density 0.067%

    No Known Activations