© 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. 7442
    Prev
    Next
    INDEX
    Explanations

    like followed by a word 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
    ire
    -0.10
    åīĥ
    -0.09
    çļĦåľ°
    -0.09
    çŁ¥æĥħ
    -0.08
    åĪ®
    -0.08
    irs
    -0.08
    éĺ´
    -0.08
    åĢĴéĹŃ
    -0.08
    èįĨå·ŀ
    -0.08
     themselves
    -0.08
    POSITIVE LOGITS
    pur
    0.09
     delt
    0.09
     Achilles
    0.08
    èĢĮè¨Ģ
    0.08
    å®ħ
    0.08
     Pur
    0.08
    ike
    0.08
    åĴĮæĬĢæľ¯
    0.08
    ikes
    0.08
    æĶĴ
    0.08
    Activations Density 0.023%

    No Known Activations