© 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. 10264
    Prev
    Next
    INDEX
    Explanations

    frozen string literal or related states

    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
    稷
    -0.10
    æĸĩåĮĸ建设
    -0.10
    ENA
    -0.09
    åĿĬ
    -0.09
    åŁŃ
    -0.09
    亢
    -0.09
    Africa
    -0.09
    mania
    -0.08
    UBE
    -0.08
    eco
    -0.08
    POSITIVE LOGITS
    åĨ°
    0.17
    åĨ°éĽª
    0.16
    åĨ»
    0.15
    åĨ»ç»ĵ
    0.13
    å¯ĴåĨ·
    0.13
    åĨ°æ·ĩæ·ĭ
    0.13
     ice
    0.12
    å¯Ĵ
    0.12
     colder
    0.12
    åĨ°åĨ·
    0.12
    Activations Density 0.066%

    No Known Activations