© 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. 62672
    Prev
    Next
    INDEX
    Explanations

    places names

    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
    -yard
    -0.10
    å®ĺåı¸
    -0.10
    械
    -0.09
    身边çļĦ
    -0.09
    辦æ³ķ
    -0.09
    æ¿Ĵ临
    -0.09
    oss
    -0.09
    ç»°
    -0.09
    嵬
    -0.09
    åľ¨çĶŁæ´»ä¸Ń
    -0.09
    POSITIVE LOGITS
    åIJģ
    0.10
    elan
    0.10
    对该
    0.09
    æŃ¤äºº
    0.09
    沫
    0.09
    cco
    0.08
    dash
    0.08
    bedo
    0.08
    Leaks
    0.08
    .flex
    0.08
    Activations Density 0.073%

    No Known Activations