© 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. 51406
    Prev
    Next
    INDEX
    Explanations

    idiomatic phrases or phrasal verbs

    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
     Conway
    -0.09
    /from
    -0.08
    è¾ĵäºĨ
    -0.08
    æĻ®
    -0.08
    åı¯éĿłæĢ§
    -0.08
    ä»Ģä¹ĪæĦıæĢĿ
    -0.08
    æįĤ
    -0.07
    à¦ĵ
    -0.07
    çķ¸
    -0.07
    zem
    -0.07
    POSITIVE LOGITS
     опÑĭ
    0.10
    æĭį
    0.09
    å²ij
    0.09
    /jav
    0.09
    еÑģп
    0.09
    æĢ§åĴĮ
    0.08
    ç½Ħ
    0.08
    еÑĤÑģÑı
    0.08
    assed
    0.08
    irim
    0.08
    Activations Density 0.191%

    No Known Activations