© 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. 57610
    Prev
    Next
    INDEX
    Explanations

    find out

    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
     Ministers
    -0.08
    ahi
    -0.08
    ember
    -0.08
     Courtesy
    -0.08
    .shutdown
    -0.08
    _SEND
    -0.08
    ados
    -0.08
    鹬
    -0.08
    autos
    -0.07
    严ç¦ģ
    -0.07
    POSITIVE LOGITS
    oup
    0.10
    æĶĴ
    0.10
    çŁį
    0.10
    ä»İä¸Ń
    0.09
    ngr
    0.09
    æ£ĺ
    0.09
    æŁ©
    0.09
     hang
    0.09
    åĨľåī¯
    0.09
    éĴŁ
    0.09
    Activations Density 0.054%

    No Known Activations