© 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. 9886
    Prev
    Next
    INDEX
    Explanations

    your guys help

    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
    èī¯
    -0.11
    åħ¶æīĢ
    -0.11
    修订
    -0.10
    شت
    -0.09
    导å¸Ī
    -0.09
    alık
    -0.09
    etzt
    -0.08
     pigment
    -0.08
    places
    -0.08
    inance
    -0.08
    POSITIVE LOGITS
    çĭ¬æľīçļĦ
    0.10
    ä¸ĵ享
    0.09
    Ñij
    0.09
    çıº
    0.08
    argo
    0.08
    çĻ½èī²çļĦ
    0.08
    ä¸Ģå¥Ĺ
    0.08
    为é¦ĸ
    0.08
    ä»Ģä¹Īäºĭ
    0.08
     Hera
    0.08
    Activations Density 0.080%

    No Known Activations