© 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. 34950
    Prev
    Next
    INDEX
    Explanations

    best possible

    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
    à¹Ĩ
    -0.09
    rect
    -0.08
     à¹Ĩ
    -0.08
    ãĤīãģĹãģĦ
    -0.08
    MEA
    -0.08
    antes
    -0.08
    å¾Īæľī
    -0.08
    åIJĬ
    -0.07
    åħ¸åŀĭçļĦ
    -0.07
    иÑĨÑĭ
    -0.07
    POSITIVE LOGITS
    åı£æ°Ķ
    0.11
    å¿ĥ头
    0.10
    .getResult
    0.10
    .DIS
    0.09
    è§ģåĪ°
    0.09
    åįıåĬ©
    0.09
    è§Ħ模æľĢ大
    0.09
    çķĶ
    0.09
    åºŀ大
    0.09
    апÑĢ
    0.09
    Activations Density 0.006%

    No Known Activations