© 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. 30494
    Prev
    Next
    INDEX
    Explanations

    OBD check engine light

    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
    å¾Ħ
    -0.10
    泡
    -0.10
    å¾ij
    -0.09
     Beit
    -0.09
    eree
    -0.09
    åħ¶å®ŀ
    -0.09
    ä¸ŃåĽ½äººæ°ij
    -0.09
    bour
    -0.09
    icer
    -0.09
    èĢ³æľº
    -0.08
    POSITIVE LOGITS
    å¾µ
    0.09
    触åıĬ
    0.09
     воÑĤ
    0.09
    çŀĴ
    0.09
    åĩıæİĴ
    0.09
    èģĶç½ij
    0.08
    åIJĦè¡Į
    0.08
    åĨħåľ°
    0.08
    èµĸ以çĶŁåŃĺ
    0.08
    pace
    0.08
    Activations Density 0.111%

    No Known Activations