© 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. 49644
    Prev
    Next
    INDEX
    Explanations

    as published

    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
    ä¸Ģç§į
    -0.11
    вали
    -0.10
    ä¸ºæľŁ
    -0.10
     ÑħоÑĤÑı
    -0.10
    zelf
    -0.10
    çĶļèĩ³
    -0.10
    Ñħа
    -0.10
    ITAL
    -0.09
    very
    -0.09
    æĺ¯ä»Ģä¹Ī
    -0.09
    POSITIVE LOGITS
    sembles
    0.17
    sembl
    0.17
    paragus
    0.16
    phalt
    0.15
     follows
    0.15
    pects
    0.15
    cribing
    0.15
    cribed
    0.15
    sembled
    0.15
     opposed
    0.14
    Activations Density 0.362%

    No Known Activations