© 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. 36149
    Prev
    Next
    INDEX
    Explanations

    adherence and compliance

    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
    é¼ł
    -0.10
    RELEASE
    -0.10
    orm
    -0.09
     Ðļа
    -0.09
    æıĸ
    -0.09
    ç»ŀ
    -0.09
    åĩºæīĭ
    -0.09
    æıIJæĹ©
    -0.08
     RELEASE
    -0.08
    æĶ¾è¿ĩ
    -0.08
    POSITIVE LOGITS
     adherence
    0.11
     compliance
    0.11
     Compliance
    0.10
    æ¯ħåĬĽ
    0.10
    è·Łè¸ª
    0.09
    éģµå®Ī
    0.09
    失èIJ½
    0.09
    herence
    0.09
    éģµ
    0.09
    çĿ£å¯¼
    0.09
    Activations Density 0.336%

    No Known Activations