© 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. 11882
    Prev
    Next
    INDEX
    Explanations

    income security

    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
    hood
    -0.09
    件äºĭ
    -0.09
    é¢Ĺ
    -0.09
    åıįåĩ»
    -0.09
    å¾·åĽ½
    -0.09
    .SDK
    -0.09
    åĬŀ好
    -0.09
    -sdk
    -0.09
    æİ¥å¾ħ
    -0.09
    æĬ¢æķij
    -0.09
    POSITIVE LOGITS
    åĬ¡å·¥
    0.10
    è°ĭ
    0.09
    alic
    0.09
     insecure
    0.09
    eland
    0.09
    itch
    0.09
    æĢ»æĶ¶åħ¥
    0.09
    ush
    0.09
    ç³Ĭ
    0.09
    å·¥åľ°
    0.08
    Activations Density 0.106%

    No Known Activations