© 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. 63117
    Prev
    Next
    INDEX
    Explanations

    going to

    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
    éŀŃ
    -0.11
    åģļæ³ķ
    -0.10
    lox
    -0.09
     sideline
    -0.09
    ä»İæѤ
    -0.09
    åĨĢ
    -0.09
    çĪ±ä½ł
    -0.09
    kick
    -0.08
    .nc
    -0.08
    æīĢæıIJä¾ĽçļĦ
    -0.08
    POSITIVE LOGITS
    æĭĸ
    0.11
    åĪ°æľĢåIJİ
    0.11
    çºłç¼ł
    0.09
    åĪ°äºĨ
    0.09
     tạp
    0.09
    å°ĺ
    0.09
     Gn
    0.09
    èĢĹ
    0.09
    drag
    0.09
    èĢĹè´¹
    0.08
    Activations Density 0.092%

    No Known Activations