© 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. 21396
    Prev
    Next
    INDEX
    Explanations

    know if or whether

    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
    .try
    -0.09
    ÑģлÑĥÑĪ
    -0.09
    _STMT
    -0.09
    ä¾Ľ
    -0.08
    åĬ©éķ¿
    -0.08
    ych
    -0.08
    æķħæĦı
    -0.08
    PRINTF
    -0.08
    .annot
    -0.08
    ENO
    -0.08
    POSITIVE LOGITS
    å°±çŁ¥éģĵ
    0.26
    çŁ¥éģĵ
    0.19
    çŁ¥æĻĵ
    0.17
    ä»ĸçŁ¥éģĵ
    0.16
    æīįçŁ¥éģĵ
    0.16
    çŁ¥éģĵèĩªå·±
    0.15
    åı¯çŁ¥
    0.15
     knows
    0.15
     know
    0.15
    éĥ½çŁ¥éģĵ
    0.15
    Activations Density 0.081%

    No Known Activations