© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37699
    Prev
    Next
    INDEX
    Explanations

    transport and transporters

    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
    åıijåĩº
    -0.10
    /engine
    -0.10
    æ¯ģçģŃ
    -0.09
    馥
    -0.09
     Armour
    -0.09
    ime
    -0.09
    容è²Į
    -0.09
    [property
    -0.09
    Radians
    -0.09
    æĽ´è¦ģ
    -0.09
    POSITIVE LOGITS
    éĻ·éĺ±
    0.10
    èĢķåľ°
    0.09
    çĶ°
    0.09
    ап
    0.08
    Tester
    0.08
    个å¤ļ
    0.08
    èĦĤèĤª
    0.08
    éĻIJ
    0.08
     UA
    0.08
    ells
    0.08
    Activations Density 0.436%

    No Known Activations