© 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. 4480
    Prev
    Next
    INDEX
    Explanations

    norovirus, Mencken, RoboCop, land, Aberhart

    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
    å¸Ī
    -0.11
    AMPLE
    -0.10
    罩
    -0.10
    è¹Ń
    -0.09
    åİĦ
    -0.09
    ÙĦع
    -0.09
    åĨ¤
    -0.09
    åı£ä¸Ń
    -0.09
    åıĹ访èĢħ
    -0.09
    é¹Ĭ
    -0.09
    POSITIVE LOGITS
    çļĦçIJĨæĥ³
    0.08
    istic
    0.08
    oldt
    0.08
    gers
    0.08
    sv
    0.08
    iber
    0.08
    çIJĨæĥ³
    0.08
    èļĵ
    0.08
    ä¸ĵ线
    0.08
    æŀľ
    0.07
    Activations Density 0.010%

    No Known Activations