© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 955
    Prev
    Next
    INDEX
    Explanations

    check if

    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
    chaft
    -0.10
    æ·±å¤Ħ
    -0.10
    olio
    -0.10
    ILITY
    -0.09
    auge
    -0.09
    ayout
    -0.09
    èĽĭ
    -0.09
    astr
    -0.09
    avn
    -0.09
    flate
    -0.09
    POSITIVE LOGITS
    icles
    0.12
    ered
    0.12
    able
    0.11
    å°Ķæĸ¯
    0.11
    outs
    0.11
    rooms
    0.10
    mate
    0.10
    mere
    0.10
    weigh
    0.10
    ìĤ¬íķŃ
    0.09
    Activations Density 0.066%

    No Known Activations