© 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. 61160
    Prev
    Next
    INDEX
    Explanations

    explain to me

    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
    åĬłçıŃ
    -0.09
    é³ı
    -0.09
    _indent
    -0.08
    ATHER
    -0.08
     ведÑĮ
    -0.08
    èĬ½
    -0.08
    微信åı·
    -0.08
    æīĢæıIJä¾ĽçļĦ
    -0.08
    è¬Ģ
    -0.08
    æĭ¿æĿ¥
    -0.08
    POSITIVE LOGITS
    讵
    0.10
    大家
    0.09
    äºĨå¤ļå°ij
    0.09
     Straw
    0.09
     literature
    0.09
    榴
    0.09
    _PROP
    0.08
    chos
    0.08
    loat
    0.08
    eree
    0.08
    Activations Density 0.021%

    No Known Activations