© 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. 54655
    Prev
    Next
    INDEX
    Explanations

    Pixar, Up, Woody Allen, Marty McFly

    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
    ỳ
    -0.09
     Eaton
    -0.09
     ridden
    -0.09
     saturn
    -0.09
     hoops
    -0.09
     Cannon
    -0.08
    å¤ļåľ°
    -0.08
    .geo
    -0.08
     maté
    -0.08
    breadcrumb
    -0.08
    POSITIVE LOGITS
     بÙĪ
    0.09
    ä¸įéĶĪ
    0.09
    饺
    0.09
    çĺª
    0.09
    ä¸ĸ
    0.08
    åĽŀé¦ĸ
    0.08
    ml
    0.08
    ä¾Ŀ
    0.08
    å¾ģæ±ĤæĦıè§ģ
    0.08
    unsch
    0.08
    Activations Density 0.010%

    No Known Activations