© 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. 33566
    Prev
    Next
    INDEX
    Explanations

    utopian or dystopian communities

    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
    éĴ§
    -0.11
    ÅĤÄĻ
    -0.09
    alive
    -0.09
    -animate
    -0.09
    èĩ³å°Ĭ
    -0.09
    inch
    -0.09
    lein
    -0.08
    avig
    -0.08
    outs
    -0.08
    prene
    -0.08
    POSITIVE LOGITS
    çIJĨæĥ³çļĦ
    0.10
    çIJĨæĥ³
    0.09
    opian
    0.09
    æĻ¯è±¡
    0.09
    建æĪIJåIJİ
    0.09
    å¢ħ
    0.09
    人çī©
    0.09
    æıĸ
    0.09
    社ä¼ļæ²»çIJĨ
    0.09
    engl
    0.09
    Activations Density 0.008%

    No Known Activations