© 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. 21562
    Prev
    Next
    INDEX
    Explanations

    like many others

    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
    èıĺ
    -0.10
    tá
    -0.10
    罡
    -0.10
    ration
    -0.09
    æ³ħ
    -0.09
     Lug
    -0.09
    å¸ĪèĮĥ
    -0.09
    alin
    -0.09
    çĸĹç¨ĭ
    -0.09
    人æĿĥ
    -0.09
    POSITIVE LOGITS
    vest
    0.08
    setw
    0.08
    æīª
    0.08
    èĩªè´Ł
    0.08
    åı¬
    0.08
    æģĭ
    0.08
    DI
    0.08
    Paste
    0.08
    (outfile
    0.07
     wrest
    0.07
    Activations Density 0.011%

    No Known Activations