© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10219
    Prev
    Next
    INDEX
    Explanations

    low values or reductions

    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
    .gs
    -0.10
    ç»Ī身
    -0.10
    ä¸įåłª
    -0.09
    è¿Ľé¡¹
    -0.09
    çļĦåĬŀæ³ķ
    -0.09
    YPE
    -0.09
    _PROVIDER
    -0.08
    /Gate
    -0.08
     Herman
    -0.08
     postData
    -0.08
    POSITIVE LOGITS
    æįŁèĢĹ
    0.11
    æĬŁ
    0.10
    -loss
    0.10
     loss
    0.09
    å®ļå±ħ
    0.09
    èĻ
    0.09
    ä¸ĢéŨ
    0.09
    loss
    0.09
    Loss
    0.09
    åĮħ袱
    0.09
    Activations Density 0.321%

    No Known Activations