© 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. 57596
    Prev
    Next
    INDEX
    Explanations

    missed all or almost all

    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
    severity
    -0.09
    è¿Ļ份
    -0.09
    è¿Ļ家ä¼Ļ
    -0.09
    åħĪçĶŁ
    -0.09
    ä¹ĭæĪĺ
    -0.09
    ä¼ī
    -0.08
    çªģçł´åı£
    -0.08
    éŃĦ
    -0.08
    èį¯ä¸ļ
    -0.08
    模èĮĥ
    -0.08
    POSITIVE LOGITS
    æ¶İ
    0.11
    æĶĴ
    0.09
    Ìģ
    0.09
    lica
    0.09
    åĨįéĢł
    0.09
    å·²ä¹ħ
    0.09
    affe
    0.09
    ifié
    0.08
    以èĩ³äºİ
    0.08
    æijĪ
    0.08
    Activations Density 0.006%

    No Known Activations