© 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. 47779
    Prev
    Next
    INDEX
    Explanations

    metastasis or metastatic

    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
     hå
    -0.10
     Keeper
    -0.09
    æ¨Ĺ
    -0.09
    .Persistent
    -0.09
    æ¼²
    -0.09
    èįŁ
    -0.09
    åĨį说
    -0.09
    expired
    -0.09
    åĪĽä½ľ
    -0.08
    æ§Į
    -0.08
    POSITIVE LOGITS
    æī©æķ£
    0.11
    转移åĪ°
    0.10
     spread
    0.10
    èĶĵ延
    0.10
     Spread
    0.09
    åij¨åĽ´çļĦ
    0.09
    转移
    0.09
    ì°¸
    0.09
    移
    0.09
     spreading
    0.09
    Activations Density 0.151%

    No Known Activations