© 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. 4797
    Prev
    Next
    INDEX
    Explanations

    donation

    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
    mino
    -0.10
    à¹Į
    -0.10
    erner
    -0.10
    iness
    -0.09
    ness
    -0.09
    stakes
    -0.09
    mina
    -0.09
    ighth
    -0.09
    好äºĭ
    -0.09
    mania
    -0.09
    POSITIVE LOGITS
    ary
    0.10
    æģ¤
    0.10
    uitive
    0.09
    aire
    0.09
    etsk
    0.09
    Ñĩик
    0.08
    eware
    0.08
    åĪ¶åº¦æĶ¹éĿ©
    0.08
    exter
    0.08
    ably
    0.08
    Activations Density 0.015%

    No Known Activations