© 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. 31497
    Prev
    Next
    INDEX
    Explanations

    in order to

    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
    åĤ¬
    -0.10
    çĶ±äºİ
    -0.10
    为äºĨ
    -0.10
    Due
    -0.09
    审
    -0.09
    zew
    -0.09
    çĶ±æĸ¼
    -0.09
    ä¹Łèĥ½
    -0.08
    stad
    -0.08
    ilos
    -0.08
    POSITIVE LOGITS
    å°±å¿ħé¡»
    0.13
    ä¼łç»Łäº§ä¸ļ
    0.10
    ä¸įæĸŃåľ°
    0.10
    è¿ĺéľĢ
    0.10
    ãĤĦãģ¯ãĤĬ
    0.10
    å°±å¾Ĺ
    0.10
    åĬ£åĬ¿
    0.09
    å°±éľĢè¦ģ
    0.09
    好åIJĹ
    0.09
    纶
    0.09
    Activations Density 0.386%

    No Known Activations