© 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. 38826
    Prev
    Next
    INDEX
    Explanations

    location prepositions

    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
    Jam
    -0.09
    /MIT
    -0.09
    osoph
    -0.09
    æĸ¥
    -0.09
    å½ĵåį³
    -0.09
    inel
    -0.09
     Äijạo
    -0.09
    strom
    -0.09
    ä¸ĭåįĬåľº
    -0.08
    inem
    -0.08
    POSITIVE LOGITS
    社ä¼ļç»Ħç»ĩ
    0.09
    大åѦæ¯ķä¸ļ
    0.09
    åķľ
    0.08
    磫
    0.08
    å°º
    0.08
    ç½ijè´Ń
    0.08
    èĭ·
    0.08
    unce
    0.08
    unkt
    0.08
     clockwise
    0.08
    Activations Density 0.053%

    No Known Activations