© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7347
    Prev
    Next
    INDEX
    Explanations

    what is

    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
    iku
    -0.09
    èµĤ
    -0.08
    åħħå®ŀ
    -0.08
    æºī
    -0.08
    ëĸ¡
    -0.08
    IVES
    -0.08
    çĶ¨æĪ·ä½ĵéªĮ
    -0.08
    zik
    -0.08
    [to
    -0.08
    LOCKS
    -0.08
    POSITIVE LOGITS
    éĥ½è®¤ä¸º
    0.09
     Noel
    0.08
    вен
    0.08
    åįģéĩĮ
    0.08
    æį®æѤ
    0.08
    mur
    0.08
    elas
    0.08
     наи
    0.08
    侧
    0.08
    uest
    0.08
    Activations Density 0.032%

    No Known Activations