© 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. 19248
    Prev
    Next
    INDEX
    Explanations

    As with

    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
    è¦ģä¹Ī
    -0.10
    =out
    -0.10
    çļĦå°±æĺ¯
    -0.10
    å½Ģ
    -0.10
    itics
    -0.09
    å®Įç¾İ
    -0.09
    jiang
    -0.09
    æıĸ
    -0.09
    encers
    -0.09
    ouble
    -0.09
    POSITIVE LOGITS
     any
    0.13
    ä»»ä½ķ
    0.11
    ä»»ä½ķæŶåĢĻ
    0.10
    any
    0.09
     many
    0.09
    åħ¶å®ĥéĹ®é¢ĺ
    0.09
    ä¸Ģç¬Ķ
    0.09
    ä¸Ģ项
    0.09
    ä¸Ģéĺµ
    0.09
     лÑİбом
    0.08
    Activations Density 0.004%

    No Known Activations