© 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. 18391
    Prev
    Next
    INDEX
    Explanations

    place names and locations

    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
    横
    -0.09
    _named
    -0.08
    è¿Ļ座åŁİå¸Ĥ
    -0.08
    éĦĻ
    -0.08
    é¡¿
    -0.08
     ears
    -0.07
    fort
    -0.07
    pany
    -0.07
     se
    -0.07
     Reggie
    -0.07
    POSITIVE LOGITS
    AZY
    0.10
    ä¹ŁæĪIJ为
    0.09
    antly
    0.09
    ALLED
    0.09
    edback
    0.09
    åĽŃ
    0.09
    èĺ§
    0.09
    .gf
    0.09
    çľģ级
    0.09
     kẻ
    0.09
    Activations Density 0.120%

    No Known Activations