© 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. 11312
    Prev
    Next
    INDEX
    Explanations

    spatial 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
    éĢļçķħ
    -0.09
    æīĢåľ¨åľ°
    -0.08
    éĻ¤éĿŀ
    -0.08
    è¶ĭ
    -0.08
    DAQ
    -0.08
    è´¨åľ°
    -0.08
    çIJĨæĻº
    -0.07
    ä¸ºæľŁ
    -0.07
    åģ¿
    -0.07
    uo
    -0.07
    POSITIVE LOGITS
    è§ĴèIJ½
    0.11
    utron
    0.10
    éĹ¯
    0.09
    ä¸įè¿ľå¤Ħ
    0.09
    vron
    0.09
    åĿŀ
    0.09
    夹
    0.09
    msp
    0.09
    æŁIJä¸Ģ
    0.08
    camp
    0.08
    Activations Density 0.149%

    No Known Activations