© 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. 11299
    Prev
    Next
    INDEX
    Explanations

    deer or deer-like creatures

    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
    ting
    -0.11
    ãģĵãģ¨
    -0.10
    atoes
    -0.09
    大楼
    -0.09
    驾é©Ń
    -0.09
    å·¨æĺŁ
    -0.09
    è¾ĸ
    -0.09
    ëģĶ
    -0.09
    人æ°Ķ
    -0.09
    ãģĥ
    -0.09
    POSITIVE LOGITS
    lijk
    0.09
    lac
    0.09
    avit
    0.09
    lage
    0.09
    theless
    0.09
    lijke
    0.09
    uate
    0.09
    mony
    0.08
     Hayden
    0.08
    pedia
    0.08
    Activations Density 0.007%

    No Known Activations