© 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. 33823
    Prev
    Next
    INDEX
    Explanations

    deemed a substitute

    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
    meter
    -0.09
    loud
    -0.08
    ÑĢоз
    -0.08
     Meter
    -0.08
    ä¸įæĽ¾
    -0.08
    æĦĪ
    -0.08
    ìľ¼
    -0.08
    طا
    -0.08
    .netbeans
    -0.08
    åı³
    -0.07
    POSITIVE LOGITS
    è¿Ļæī¹
    0.09
    éĥĬåĮº
    0.09
    _mC
    0.09
    cant
    0.09
    大家éĥ½åľ¨
    0.09
    æĹłæĥħ
    0.08
    -any
    0.08
    onne
    0.08
    åijĬè¯ī大家
    0.08
    éĵ¢
    0.08
    Activations Density 0.004%

    No Known Activations