© 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. 5913
    Prev
    Next
    INDEX
    Explanations

    starting premise or point

    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
    iams
    -0.10
    xCA
    -0.10
    常å§Ķ
    -0.09
    xDB
    -0.09
    åIJŀåĻ¬
    -0.09
     rej
    -0.09
    FLAGS
    -0.09
    é«ĺçŃīåŃ¦æł¡
    -0.08
    aura
    -0.08
    庥
    -0.08
    POSITIVE LOGITS
    åĩºåıij
    0.12
    端æŃ£
    0.10
    èµ·çĤ¹
    0.10
    æİĸ
    0.09
    ãĤħ
    0.09
     condition
    0.09
    被迫
    0.09
    åĪĿå¿ĥ
    0.09
    æĢ§åij½
    0.08
    çģµæĦŁ
    0.08
    Activations Density 0.065%

    No Known Activations