© 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. 11177
    Prev
    Next
    INDEX
    Explanations

    closing parentheses or punctuation

    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
    çļĦåĪ°æĿ¥
    -0.09
    оÑĢа
    -0.09
    诸å¦Ĥ
    -0.09
    人äºĭ
    -0.09
    æīĢè°ĵçļĦ
    -0.09
    åĵªéĩĮ
    -0.09
    å°±æĦıåij³çĿĢ
    -0.09
    æ¶īåıĬåĪ°
    -0.08
     Consort
    -0.08
    raf
    -0.08
    POSITIVE LOGITS
    .elem
    0.10
    ROLE
    0.09
    æ±°
    0.08
    å·²ä¹ħ
    0.08
    éĹ¹
    0.08
    åıŁ
    0.08
     lẫn
    0.08
     anv
    0.07
    ued
    0.07
    _decay
    0.07
    Activations Density 0.223%

    No Known Activations