© 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. 2823
    Prev
    Next
    INDEX
    Explanations

    author names and publications

    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
    еÑĢÑĮ
    -0.10
    å«Įçĸij
    -0.10
    éĩIJ
    -0.10
    åħ¶å®ĥéĹ®é¢ĺ
    -0.10
    缨
    -0.09
    ä¸Ģåij³
    -0.09
    裹
    -0.09
    ibling
    -0.09
    ç¬Ķ
    -0.09
    å·³
    -0.09
    POSITIVE LOGITS
    æģ»
    0.09
    éĻ¡
    0.08
     Sho
    0.08
    æ¢Ń
    0.07
     Nou
    0.07
    ︵
    0.07
    å¸ĪåĤħ
    0.07
     unpublished
    0.07
    enger
    0.07
    çľĭå¾Ĺ
    0.07
    Activations Density 0.029%

    No Known Activations