© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10263
    Prev
    Next
    INDEX
    Explanations

    estimated numbers

    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
    nit
    -0.11
    adan
    -0.10
    ëĭ¤ê°Ģ
    -0.09
    acha
    -0.09
    èĨº
    -0.09
    ãģ¾ãģķ
    -0.09
    å®ŀå®ŀåľ¨åľ¨
    -0.09
    è§Ħå®ļçļĦ
    -0.09
    设计æĸ¹æ¡Ī
    -0.09
    erer
    -0.08
    POSITIVE LOGITS
    ably
    0.10
    äºĨä¸Ģä¸ĭ
    0.10
    ions
    0.09
    ëĵľë¦¬
    0.09
    ¡
    0.09
    gle
    0.09
    /pro
    0.09
    iy
    0.09
    éĵ¬
    0.09
    ãĤĤãĤī
    0.08
    Activations Density 0.033%

    No Known Activations