© 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. 29598
    Prev
    Next
    INDEX
    Explanations

    absurd / absurdly / absurdities

    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
    som
    -0.10
    ander
    -0.09
    ëģĶ
    -0.09
    enen
    -0.09
    eters
    -0.09
    rons
    -0.09
    å¿IJ
    -0.08
    èĤŁ
    -0.08
    _shuffle
    -0.08
    åī¿
    -0.08
    POSITIVE LOGITS
    ities
    0.14
    ity
    0.13
    ly
    0.13
    ively
    0.11
    ous
    0.10
    ITIES
    0.10
    ä¹ĭå¤Ħ
    0.10
    -minded
    0.10
    éĻ¬
    0.09
    ä¹ĭ举
    0.09
    Activations Density 0.002%

    No Known Activations