© 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. 27990
    Prev
    Next
    INDEX
    Explanations

    placement and position

    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
    å³¥
    -0.09
    stery
    -0.09
    iec
    -0.09
    å½ĵåľ°
    -0.08
     дог
    -0.08
    ä¸¤åľ°
    -0.08
     Herbal
    -0.08
    entine
    -0.08
    èħ¹éĥ¨
    -0.08
    åįĹéĥ¨
    -0.08
    POSITIVE LOGITS
    ä½įç½®
    0.15
    çļĦä½įç½®
    0.14
     placement
    0.14
    å®īç½®
    0.12
    æĶ¾ç½®
    0.12
     Placement
    0.12
    Placement
    0.12
    æijĨæĶ¾
    0.12
    .position
    0.12
     Position
    0.12
    Activations Density 0.187%

    No Known Activations