© 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. 62490
    Prev
    Next
    INDEX
    Explanations

    sublime, lofty, exalted, expression

    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
    PRI
    -0.10
    ð¨±
    -0.09
    _IMPL
    -0.09
    æĪIJè¯Ń
    -0.09
    orial
    -0.09
    æĸ¤
    -0.08
    vla
    -0.08
    æĭĹ
    -0.08
    ORTH
    -0.08
    apas
    -0.08
    POSITIVE LOGITS
    adder
    0.11
    -minded
    0.10
    0.10
    ending
    0.10
    åįĩåįİ
    0.10
    ãģ£ãģ±
    0.09
    pher
    0.09
    ishments
    0.09
    åıijè§ī
    0.08
    åĵī
    0.08
    Activations Density 0.003%

    No Known Activations