© 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. 17456
    Prev
    Next
    INDEX
    Explanations

    names of people and places

    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
    天涯
    -0.10
    鹧
    -0.09
    åŀĤ
    -0.09
    ä¿ĥæĪIJ
    -0.09
    亵
    -0.09
    æı©
    -0.08
    èĤ¤
    -0.08
    大æ°Ķ
    -0.08
    ä¿ĥè¿Ľ
    -0.08
    çŁŃæľŁåĨħ
    -0.08
    POSITIVE LOGITS
    使æĪij
    0.09
    两个å°ıæŶ
    0.08
    好åıĭ
    0.08
    绣çŃ¹æİ¨è¿Ľ
    0.08
    Compat
    0.08
    çĹķ
    0.08
    åħ©äºº
    0.08
    Homepage
    0.08
    .timing
    0.07
    .getLength
    0.07
    Activations Density 0.501%

    No Known Activations