© 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. 30838
    Prev
    Next
    INDEX
    Explanations

    geographical 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
    çݳ
    -0.10
    onium
    -0.10
     STDCALL
    -0.09
    æ±°
    -0.09
    ðŁĪ
    -0.09
    å¥ĸ
    -0.09
    Paused
    -0.09
    -pencil
    -0.09
    åĽ½åĢº
    -0.09
     WARRANTY
    -0.09
    POSITIVE LOGITS
    ä¹Ķ
    0.09
    t
    0.08
    æŁ¥è¯¢
    0.08
    åij¨è¾¹
    0.08
    ois
    0.08
    åĭĥåĭĥ
    0.08
    iola
    0.08
    utan
    0.07
     amen
    0.07
    te
    0.07
    Activations Density 0.160%

    No Known Activations