© 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. 30358
    Prev
    Next
    INDEX
    Explanations

    ministry or minister

    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
    ervo
    -0.11
    avo
    -0.10
    åħļå§Ķ
    -0.09
    å¢ī
    -0.09
    ç¾ļ
    -0.09
    eries
    -0.09
    NESS
    -0.09
    edom
    -0.08
    periment
    -0.08
    spm
    -0.08
    POSITIVE LOGITS
    Ľå»º
    0.10
    itest
    0.09
     Hastings
    0.09
     Ced
    0.09
    æľīéĻIJåħ¬åı¸
    0.08
    çij°
    0.08
    mpr
    0.08
    ожно
    0.08
    æīĭèħķ
    0.08
    isor
    0.08
    Activations Density 0.010%

    No Known Activations