© 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. 36015
    Prev
    Next
    INDEX
    Explanations

    not followed by contrasting ideas

    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
    dre
    -0.09
    ä¸įå°ij
    -0.08
    æľ¬è´¨ä¸Ĭ
    -0.08
    ddy
    -0.08
    è¿ĺæĥ³
    -0.08
     bod
    -0.08
    ä¸īçĤ¹
    -0.08
    oke
    -0.08
    neau
    -0.08
    å½ķ
    -0.07
    POSITIVE LOGITS
    _ur
    0.11
    ocos
    0.10
    鸢
    0.10
    çĹ¢
    0.10
    phans
    0.10
    ä»ħä»ħ
    0.09
    otate
    0.09
     поÑģл
    0.09
    URT
    0.09
    磧
    0.09
    Activations Density 0.029%

    No Known Activations