© 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. 56185
    Prev
    Next
    INDEX
    Explanations

    out there

    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
    Ñģ
    -0.08
    ä¸įäºĨ
    -0.08
    arro
    -0.08
    åľ¨ç¾İåĽ½
    -0.07
    maker
    -0.07
    ä¸Ńåħ³
    -0.07
    æľ¦èĥ§
    -0.07
    èįª
    -0.07
    ä½ĵåĨħ
    -0.07
     univers
    -0.07
    POSITIVE LOGITS
    çIJ¬
    0.11
    abouts
    0.11
    andel
    0.10
    åµĺ
    0.10
    atern
    0.09
    èĻij
    0.09
    媳
    0.09
    onet
    0.09
    èĮ«èĮ«
    0.09
    oring
    0.09
    Activations Density 0.006%

    No Known Activations