© 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. 3567
    Prev
    Next
    INDEX
    Explanations

    lack or loss

    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
    该æ¡Ī
    -0.09
    eo
    -0.09
    íľĺ
    -0.08
    çīĩ
    -0.08
    èĪ¶
    -0.08
    غر
    -0.08
    signals
    -0.08
    çĽĪ
    -0.08
    centage
    -0.08
    ura
    -0.08
    POSITIVE LOGITS
    è¿ĩ大
    0.14
    太大
    0.12
    太é«ĺ
    0.12
    太快
    0.12
    -too
    0.11
     too
    0.11
    太å¤ļ
    0.10
    æīĢèĩ´
    0.10
    çŃīåİŁåĽł
    0.10
     ÙĪعدÙħ
    0.10
    Activations Density 0.220%

    No Known Activations