© 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. 18449
    Prev
    Next
    INDEX
    Explanations

    hypothesis and theories

    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
    anto
    -0.09
    æī¿è¯º
    -0.09
    æ³ħ
    -0.09
    ä¸Ģåıªæīĭ
    -0.09
    éĥ½ä¸įçŁ¥éģĵ
    -0.09
    è³ĩè¨Ĭ
    -0.09
    庾
    -0.09
    _UNDEF
    -0.09
    讲究
    -0.09
    ENTE
    -0.09
    POSITIVE LOGITS
    认为
    0.13
    大èĥĨ
    0.12
     hypothesis
    0.12
    åı¯èĥ½æĢ§
    0.11
     idea
    0.10
     hypotheses
    0.10
    èªįçĤº
    0.10
     alternative
    0.10
    åı¦ä¸Ģç§į
    0.09
    alternative
    0.09
    Activations Density 0.273%

    No Known Activations