© 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. 19914
    Prev
    Next
    INDEX
    Explanations

    ships

    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
     Wildcats
    -0.11
    eton
    -0.10
    触
    -0.09
    åIJĿ
    -0.09
    иÑĢÑĥ
    -0.09
    ille
    -0.09
    ately
    -0.09
    aters
    -0.09
    ä½°
    -0.09
    æĭŃ
    -0.08
    POSITIVE LOGITS
    æľŁéĹ´
    0.10
    æľŁåĨħ
    0.09
    举é£İ
    0.09
    èįĽ
    0.08
    åĴı
    0.08
    기ê°Ħ
    0.08
    ÑĦеÑĢ
    0.08
    rena
    0.08
    çļĦæľĢä½³
    0.08
    åĪ¶åº¦æĶ¹éĿ©
    0.08
    Activations Density 0.012%

    No Known Activations