© 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. 33062
    Prev
    Next
    INDEX
    Explanations

    shipping within the contiguous United States.on small items, this includes a no signature required, parcel delivery.for larger items, a signature-required threshold delivery is made`.States, UK, USA

    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
    ivid
    -0.09
    phin
    -0.09
     diam
    -0.09
    禺
    -0.08
    çĭĤ欢
    -0.08
    anim
    -0.08
     Hazel
    -0.08
    èįŁ
    -0.08
    è¿Ŀæ³ķè¡Į为
    -0.08
    sav
    -0.08
    POSITIVE LOGITS
    éĩįåŀĭ
    0.11
    èĮĥåĽ´åĨħ
    0.10
    éĿĴå°ijå¹´
    0.09
    æ³Ľ
    0.08
    åĨħçļĦ
    0.08
    éº»æľ¨
    0.08
    æľīä¸Ģå®ļçļĦ
    0.08
    åĴĮåľ°åĮº
    0.08
    ItemAt
    0.08
    eras
    0.08
    Activations Density 0.016%

    No Known Activations