© 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. 55258
    Prev
    Next
    INDEX
    Explanations

    fully followed by descriptors

    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
    sWith
    -0.15
    ively
    -0.12
    sr
    -0.10
    iness
    -0.10
    sey
    -0.09
    aly
    -0.09
    лад
    -0.09
    ont
    -0.08
    sel
    -0.08
    shan
    -0.08
    POSITIVE LOGITS
    æĪIJçĨŁçļĦ
    0.12
    åıijå±ķä¸Ń
    0.11
    ester
    0.10
    åħħ足çļĦ
    0.10
    ennes
    0.10
    åıijå±ķéĺ¶æ®µ
    0.10
    订
    0.10
    ç¿Ĵ
    0.10
    æĪIJçĨŁ
    0.09
    æ²īæµ¸åľ¨
    0.09
    Activations Density 0.011%

    No Known Activations