© 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. 31488
    Prev
    Next
    INDEX
    Explanations

    preposition followed by noun phrase

    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
    对åħ¬åı¸
    -0.10
    æŀ¶åŃIJ
    -0.09
    çĭ¬èĩª
    -0.09
    æļĤç¼ĵ
    -0.09
    å¥ĩå¦Ļ
    -0.09
    åıĤä¸İåĪ°
    -0.09
    æ§Ľ
    -0.09
    åĩłç§į
    -0.08
     Ritch
    -0.08
    è¿Ļè¾ĪåŃIJ
    -0.08
    POSITIVE LOGITS
    ãĥIJãĥ«
    0.09
    æ®Ĩ
    0.09
    ights
    0.08
    iesen
    0.08
     Muk
    0.08
    odos
    0.08
    ä¸įéĻIJ
    0.08
    åĤ¬
    0.08
    çķĭ
    0.08
    izen
    0.08
    Activations Density 0.185%

    No Known Activations