© 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. 23331
    Prev
    Next
    INDEX
    Explanations

    shape and shaping

    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
    AMA
    -0.09
    å®ļä½į
    -0.09
    igator
    -0.09
    Ju
    -0.09
    amas
    -0.09
    äºĴ缸
    -0.08
    çĦ¦çĤ¹
    -0.08
     Scot
    -0.08
    idget
    -0.08
    å°ģéĶģ
    -0.08
    POSITIVE LOGITS
    èĢĮæĪIJ
    0.13
     shaping
    0.11
     shape
    0.11
    สรร
    0.11
    shape
    0.11
    éĩįå¡ij
    0.10
     shaped
    0.10
    _SHAPE
    0.10
    æīĵéĢłåĩº
    0.10
     shapes
    0.10
    Activations Density 0.072%

    No Known Activations