© 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. 53528
    Prev
    Next
    INDEX
    Explanations

    stone's throw, stone cold, stone offers

    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
    otropic
    -0.09
    Suc
    -0.09
    ç½²
    -0.09
    Ñģлав
    -0.08
    åİ©
    -0.08
    etes
    -0.08
    ility
    -0.08
    æĪIJçĨŁ
    -0.08
    è¿Ļ件äºĭ
    -0.08
    åIJijãģį
    -0.08
    POSITIVE LOGITS
    çŁ³å¤´
    0.18
     stones
    0.16
    ä¸ĢåĿĹ
    0.15
    åĿĹ
    0.15
     stone
    0.14
    å²©çŁ³
    0.14
    å¶Ļ
    0.13
    å¡Ĭ
    0.13
    çŁ³æĿIJ
    0.13
    stones
    0.12
    Activations Density 0.082%

    No Known Activations