© 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. 35525
    Prev
    Next
    INDEX
    Explanations

    research and study

    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
    .setOutput
    -0.09
    _testing
    -0.09
    温æĥħ
    -0.09
    ç³»
    -0.09
     itemprop
    -0.09
    ç§Ń
    -0.09
    vip
    -0.09
    ÑıÑī
    -0.09
     полÑĥÑĩил
    -0.09
    æ¾Ħ
    -0.09
    POSITIVE LOGITS
    è°ĥçłĶ
    0.16
    è°ĥæŁ¥
    0.15
     research
    0.15
     researching
    0.14
    åĬŁè¯¾
    0.13
     researched
    0.13
    çłĶ究
    0.13
    research
    0.12
     иÑģÑģледованиÑı
    0.12
     иÑģÑģлед
    0.12
    Activations Density 0.100%

    No Known Activations