© 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. 40061
    Prev
    Next
    INDEX
    Explanations

    national parks, transportation, distance from

    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
    åľ¨åħ¨çIJĥ
    -0.11
    ãģĽãģĦ
    -0.10
    ä¸Ńç¾İ
    -0.09
    åĮĹç¾İ
    -0.09
    åĪ°æľŁ
    -0.09
     continents
    -0.09
    åľ¨æĹ¥æľ¬
    -0.09
    æĻĶ
    -0.09
    çĪ±å°Ķåħ°
    -0.09
    ÙĥÙĨ
    -0.09
    POSITIVE LOGITS
     Jag
    0.08
    çģµ
    0.08
    Gram
    0.08
    GetComponent
    0.08
    èij¡èIJĦ
    0.08
     Trophy
    0.08
    hdr
    0.08
    éĥĬ
    0.08
    plevel
    0.07
    æ¯Ķèµ·
    0.07
    Activations Density 0.243%

    No Known Activations