© 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. 53797
    Prev
    Next
    INDEX
    Explanations

    locations and 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
    gne
    -0.10
    è·ª
    -0.09
    ubb
    -0.09
    å®īæİĴ
    -0.09
     Isles
    -0.09
    uell
    -0.09
    askell
    -0.08
    éľĢè¦ģçĶ¨åĪ°
    -0.08
    ixels
    -0.08
    esser
    -0.08
    POSITIVE LOGITS
     unm
    0.09
    è§ĴèIJ½
    0.08
    åİĭå®ŀ
    0.08
    åı¶åŃIJ
    0.08
    毯
    0.08
    fieldname
    0.08
    ç¥ļ
    0.08
    粪
    0.08
    Comparable
    0.08
    éĢĥèĦ±
    0.08
    Activations Density 0.032%

    No Known Activations