© 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. 31575
    Prev
    Next
    INDEX
    Explanations

    among, between, in, into

    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
    çļĭ
    -0.09
     freder
    -0.08
    æŁ½
    -0.08
    次ä¼ļè®®
    -0.08
    ยà¸ģ
    -0.08
    åĶ¯ä¸ĢçļĦ
    -0.08
    çļĻ
    -0.08
    满
    -0.08
    满èĦ¸
    -0.08
     Strikes
    -0.08
    POSITIVE LOGITS
    ç¼ĿéļĻ
    0.14
    éļĻ
    0.14
    éĹ´éļĻ
    0.13
    æ·±å¤Ħ
    0.12
    æŃ»è§Ĵ
    0.12
    éļIJèĹı
    0.12
    çĬĦ
    0.11
    æİĸ
    0.11
    ãģ«åħ¥
    0.10
     Between
    0.10
    Activations Density 0.090%

    No Known Activations