© 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. 30761
    Prev
    Next
    INDEX
    Explanations

    email quoting headers

    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
    anche
    -0.09
    oton
    -0.09
    éĺħ读åħ¨æĸĩ
    -0.09
    èĩªä¹ł
    -0.09
    åĶ¯ä¸ĢçļĦ
    -0.09
    s
    -0.09
    sut
    -0.08
    ạ
    -0.08
    inning
    -0.08
    as
    -0.08
    POSITIVE LOGITS
    ifax
    0.09
    à¸Ĺะ
    0.09
    unbind
    0.08
    erring
    0.08
    gni
    0.08
    ATIVE
    0.08
    ÐĴидео
    0.08
    شت
    0.08
    è·Łéļı
    0.08
    ç§Ģ丽
    0.08
    Activations Density 0.123%

    No Known Activations