© 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. 55449
    Prev
    Next
    INDEX
    Explanations

    forgotten password or login issues

    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
    çijĦ
    -0.10
     filesystem
    -0.09
    æĦŁæŁĵèĢħ
    -0.08
    ä¸Ģèīĺ
    -0.08
    اÙħØ©
    -0.08
    ä¸Ģ天
    -0.08
    æĦĪåĬł
    -0.08
    ius
    -0.08
     pont
    -0.08
    æĿ¥çļĦ
    -0.08
    POSITIVE LOGITS
    PropertyParams
    0.10
    å«ģ
    0.09
    åĵij
    0.09
    æ®ĭçĸ¾
    0.09
    äºĨèĩªå·±çļĦ
    0.09
    ä¹Łä¸įè¦ģ
    0.08
    ritel
    0.08
    æ¸ħçĪ½
    0.08
    è·»
    0.08
    黾
    0.08
    Activations Density 0.005%

    No Known Activations