© 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. 1661
    Prev
    Next
    INDEX
    Explanations

    nutritional value

    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
    hill
    -0.11
    è¿¢
    -0.09
    GPL
    -0.09
    atic
    -0.09
    åijĹ
    -0.08
    ä¸Ģ个éĹ®é¢ĺ
    -0.08
    è¿Ļæĺ¯ä¸Ģç§į
    -0.08
    éĥľ
    -0.08
    lor
    -0.08
    paid
    -0.08
    POSITIVE LOGITS
    vas
    0.10
    å®ĮåĸĦ
    0.09
    okie
    0.09
    漩
    0.09
    istor
    0.09
    åĩ¹
    0.09
    åŃ¦å®¶
    0.08
    ven
    0.08
    iano
    0.08
    æĺ§
    0.08
    Activations Density 0.009%

    No Known Activations