© 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. 1005
    Prev
    Next
    INDEX
    Explanations

    inland or interior location

    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
    äºĮ代
    -0.10
    æĹ©æĻļ
    -0.10
    itian
    -0.09
    åĽ½æ°ij
    -0.09
    è´´å¿ĥ
    -0.09
    isko
    -0.09
    DOWN
    -0.09
    ç´¯äºĨ
    -0.09
    æķ¦
    -0.09
    à¸Ķาร
    -0.09
    POSITIVE LOGITS
    ted
    0.10
    STER
    0.10
    opa
    0.09
    çľģ份
    0.09
    areas
    0.09
    è¿ĩäºİ
    0.08
    å±Ģ
    0.08
    thr
    0.08
    ster
    0.08
     areas
    0.08
    Activations Density 0.002%

    No Known Activations