© 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. 50526
    Prev
    Next
    INDEX
    Explanations

    starts with Str

    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
    ÑģÑĤÑĢо
    -0.11
    é¦ĸ饰
    -0.10
    ÑģÑĤÑĢа
    -0.10
    imum
    -0.09
    ะ
    -0.09
    çĦ¶æĺ¯
    -0.09
    idas
    -0.09
    atron
    -0.09
    empt
    -0.09
    uality
    -0.09
    POSITIVE LOGITS
    ively
    0.14
    èĩ¾
    0.13
    pped
    0.13
    (describing
    0.10
    æĦıä¹īä¸ĬçļĦ
    0.10
    kop
    0.10
    mania
    0.09
    幺
    0.09
    ive
    0.09
    inq
    0.09
    Activations Density 0.078%

    No Known Activations