© 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. 37936
    Prev
    Next
    INDEX
    Explanations

    suffix after names/titles

    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
    unic
    -0.09
    ãģ©ãģĵãĤį
    -0.09
    URN
    -0.09
    åݨå¸Ī
    -0.08
    缺çĤ¹
    -0.08
    дел
    -0.08
    akin
    -0.08
    dÃŃ
    -0.08
    讹
    -0.08
    avit
    -0.08
    POSITIVE LOGITS
     Charm
    0.09
    سر
    0.09
    .springboot
    0.08
    éľľ
    0.08
     BASIS
    0.08
    çŃīè¡Įä¸ļ
    0.08
    å®īåħ¨ä¿Ŀéļľ
    0.08
    åĨħå¿ĥçļĦ
    0.08
    åĪĽæĸ°èĥ½åĬĽ
    0.08
    KC
    0.07
    Activations Density 0.034%

    No Known Activations