© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8469
    Prev
    Next
    INDEX
    Explanations

    scores and 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
    éĵį
    -0.10
    èµ·äºĨ
    -0.10
    å®ŀå®ŀåľ¨åľ¨
    -0.10
    åķ¤
    -0.10
    ä½ĵè´´
    -0.09
    åĮ¹
    -0.09
    æ£ĺ
    -0.09
    å®ŀè´¨æĢ§
    -0.09
    éĢłåŀĭ
    -0.09
    åįģä¸ĥ
    -0.09
    POSITIVE LOGITS
    æı¡æīĭ
    0.09
    ntl
    0.09
    bserv
    0.09
    tery
    0.09
    erview
    0.08
    bject
    0.08
    æĥĭ
    0.08
    mana
    0.08
    èIJ©
    0.08
    åĩı
    0.08
    Activations Density 0.012%

    No Known Activations