© 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. 54257
    Prev
    Next
    INDEX
    Explanations

    stable, stability, ability, stabilizing

    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
    èĥ¸æĢĢ
    -0.10
    ality
    -0.09
    pek
    -0.09
    utf
    -0.08
    elas
    -0.08
    ãĤĭãģ®ãģĮ
    -0.08
    å¾ĭ
    -0.08
    å¤©çľŁ
    -0.08
    çļĦä¹IJ趣
    -0.08
    åķĦ
    -0.08
    POSITIVE LOGITS
    稳å®ļçļĦ
    0.19
    稳å®ļ
    0.19
    ä¸į稳å®ļ
    0.16
    ç©©å®ļ
    0.15
    稳å®ļæĢ§
    0.15
    å®īå®ļ
    0.13
     stable
    0.13
     á»ķn
    0.12
     Stable
    0.12
     stability
    0.12
    Activations Density 0.094%

    No Known Activations