© 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. 5750
    Prev
    Next
    INDEX
    Explanations

    http URLs

    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
    æĻºæħ§åŁİå¸Ĥ
    -0.09
    麽
    -0.08
    дон
    -0.08
    ç½ijæ°ij
    -0.08
    æ´
    -0.08
    æ·¡åĮĸ
    -0.08
    _barrier
    -0.08
    楼
    -0.07
    èıĩ
    -0.07
    æ±Łæ¹ĸ
    -0.07
    POSITIVE LOGITS
    edin
    0.12
    LastError
    0.11
    ibre
    0.10
    åĩłå¼ł
    0.09
     Livingston
    0.09
    _RUNTIME
    0.09
    cks
    0.09
    ÉŁ
    0.09
    åŁ
    0.09
    åıijæĺİä¸ĵåĪ©
    0.09
    Activations Density 0.123%

    No Known Activations