© 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. 33812
    Prev
    Next
    INDEX
    Explanations

    specificity or specific

    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
     Cornel
    -0.09
    éĹªçĥģ
    -0.08
    loth
    -0.08
     Courier
    -0.08
    æ§Ľ
    -0.08
    ipop
    -0.08
    pk
    -0.08
    èµ·æŃ¥
    -0.08
     Sunrise
    -0.08
    å½ĵ天
    -0.08
    POSITIVE LOGITS
    æĢ§å¼º
    0.15
    æĢ§åĴĮ
    0.14
    æĢ§çļĦ
    0.12
     specificity
    0.12
    åĶ¯ä¸ĢçļĦ
    0.11
    çī¹å®ļ
    0.10
    楼å®ĩ
    0.09
    åĶ¯ä¸Ģ
    0.09
    æķıéĶIJ
    0.09
    æĿ¼
    0.09
    Activations Density 0.637%

    No Known Activations