© 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. 63183
    Prev
    Next
    INDEX
    Explanations

    fur endings

    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
    íĴĪ
    -0.10
    æĢ§å¼º
    -0.10
    ãģĹãģ¾ãģĦ
    -0.10
    em
    -0.09
    æĢģ
    -0.09
    æ²Ĥ
    -0.09
    稳妥
    -0.08
    OF
    -0.08
    ä»Ģä¹Īåij¢
    -0.08
    еÑģп
    -0.08
    POSITIVE LOGITS
    说æĺ¯
    0.16
    thest
    0.12
    uous
    0.10
    충
    0.09
    felt
    0.09
    iously
    0.09
    lessly
    0.09
    .proc
    0.09
    gence
    0.09
    /cpu
    0.08
    Activations Density 0.005%

    No Known Activations