© 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. 23160
    Prev
    Next
    INDEX
    Explanations

    location and state 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
    ä¸Ģé¢Ĺ
    -0.10
    éĴ
    -0.10
    æī£
    -0.09
    _MED
    -0.09
    æī£éĻ¤
    -0.08
    æİ¥åIJ¬
    -0.08
    åĮħåŃIJ
    -0.08
    åĩĽ
    -0.08
    ropy
    -0.08
    BitFields
    -0.08
    POSITIVE LOGITS
    ä¸ºæľŁ
    0.08
    éĹº
    0.08
     Maurit
    0.08
    椿
    0.08
    è¿ĻäºĽä¸ľè¥¿
    0.08
    ween
    0.08
    quis
    0.08
     somewhere
    0.08
    omething
    0.08
     NOTICE
    0.08
    Activations Density 0.011%

    No Known Activations