© 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. 18477
    Prev
    Next
    INDEX
    Explanations

    stars and constellations

    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
    ãĥĺãĥ«
    -0.11
    åįĪé¤IJ
    -0.11
    æıŃå¼Ģ
    -0.10
     uphill
    -0.10
    交ä»ĺ
    -0.10
    adium
    -0.10
    渲
    -0.10
    éĵº
    -0.10
     Franc
    -0.09
    _snd
    -0.09
    POSITIVE LOGITS
     stars
    0.11
    äºĺ
    0.10
    æĺŁæĺŁ
    0.09
    -stars
    0.09
    magnitude
    0.09
    æĸĹ
    0.09
     magnitude
    0.09
     const
    0.09
    çİ°è¡Į
    0.09
    äºĶæĺŁ
    0.09
    Activations Density 0.025%

    No Known Activations