© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 20737
    Prev
    Next
    INDEX
    Explanations

    questions starting with could

    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
    ively
    -0.12
    åŃIJéĩĮ
    -0.11
    ×ķת
    -0.10
    好äºĨ
    -0.09
    ays
    -0.09
    ë£Į
    -0.09
    Öģ
    -0.08
    ìľ¨
    -0.08
    ally
    -0.08
    ap
    -0.08
    POSITIVE LOGITS
    nt
    0.15
    å¤ł
    0.14
     бÑĭ
    0.12
    rey
    0.12
    ت
    0.11
    've
    0.11
    ’ve
    0.11
    زار
    0.11
    ÑģÑı
    0.11
     бÑĭÑĤÑĮ
    0.10
    Activations Density 0.077%

    No Known Activations