© 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. 30225
    Prev
    Next
    INDEX
    Explanations

    Mac App Store

    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
    èij«
    -0.10
    åħħæ²Ľ
    -0.10
    å½·
    -0.09
    odge
    -0.09
     полÑĥ
    -0.09
    æ³ķå®ļ
    -0.08
    èĴ´
    -0.08
    ally
    -0.08
    iten
    -0.08
    è·ĭ
    -0.08
    POSITIVE LOGITS
    intosh
    0.17
    rom
    0.10
    ä¹İ
    0.10
    åĩī
    0.09
    ropol
    0.09
    ../../../
    0.09
    enzie
    0.09
    rodu
    0.09
     Covenant
    0.09
    adam
    0.08
    Activations Density 0.020%

    No Known Activations