© 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. 22877
    Prev
    Next
    INDEX
    Explanations

    guarantee, trial, refund

    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
    åĨįéĢł
    -0.10
    ido
    -0.09
    é£İ湿
    -0.09
    æµĵæµĵçļĦ
    -0.09
    èįīåİŁ
    -0.08
    åįģéĩĮ
    -0.08
    æij¸ç´¢
    -0.08
    æ±Łä¸ľ
    -0.08
    åīĮ
    -0.08
    è¿Ļæī¹
    -0.08
    POSITIVE LOGITS
    æľīæľŁ
    0.09
    onian
    0.09
    管çIJĨåijĺ
    0.09
    нÑĤ
    0.08
    ä¿ĿçķĻ
    0.08
    ç«
    0.08
    é¦ĸå¯Į
    0.08
    çĬ¶åħĥ
    0.08
    èı¡
    0.08
    忤
    0.08
    Activations Density 0.063%

    No Known Activations