© 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. 47566
    Prev
    Next
    INDEX
    Explanations

    self-esteem, self-perception, self-image

    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
    Negative Logits
    _mB
    -0.09
    iani
    -0.08
    egment
    -0.08
    ä¼ļ被
    -0.08
    樾
    -0.08
    alsa
    -0.08
    illos
    -0.08
    æ±ī
    -0.08
    shal
    -0.08
    oref
    -0.08
    POSITIVE LOGITS
    verständlich
    0.13
    tle
    0.10
    é£ŀæī¬
    0.10
    ie
    0.10
    hood
    0.10
    åŁĻ
    0.10
    bie
    0.09
    lessly
    0.09
    -même
    0.09
    same
    0.09
    Activations Density 0.059%

    No Known Activations