© 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. 826
    Prev
    Next
    INDEX
    Explanations

    Ric/Ris related names and words

    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
    ../../../
    -0.13
    ¹
    -0.10
    ../../
    -0.10
    iners
    -0.09
    åĵ¡
    -0.09
    åł¡åŀĴ
    -0.09
    udu
    -0.09
    ä¹į
    -0.09
    çĩĥ
    -0.09
    rray
    -0.09
    POSITIVE LOGITS
    åĭĥåĭĥ
    0.11
    fait
    0.09
    sey
    0.08
    hte
    0.08
    outil
    0.08
    odian
    0.08
    uno
    0.08
    eway
    0.08
    ough
    0.08
    emplate
    0.08
    Activations Density 0.025%

    No Known Activations