© 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. 2838
    Prev
    Next
    INDEX
    Explanations

    BEGIN or SPDX followed by license/key identifier

    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
    è°ª
    -0.09
    -mf
    -0.09
    resse
    -0.08
    æĶ¶è´¹æłĩåĩĨ
    -0.08
    æıŃéľ²
    -0.08
    raith
    -0.08
    pad
    -0.08
    å¿ħå¤ĩ
    -0.08
    äºĽä»Ģä¹Ī
    -0.07
    ä¸įæľį
    -0.07
    POSITIVE LOGITS
    vana
    0.10
    zan
    0.10
    èĢĮä¸Ķ
    0.09
    ìĥī
    0.09
    aset
    0.09
    èĨĽ
    0.09
    oby
    0.09
     piv
    0.09
     Vanity
    0.09
    æ¾į
    0.09
    Activations Density 0.024%

    No Known Activations