© 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. 48163
    Prev
    Next
    INDEX
    Explanations

    referring to previously written posts or articles

    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
    AFE
    -0.09
    ONS
    -0.09
    åĽŀæĥ³
    -0.08
    è¶ĬæĿ¥è¶Ĭ大
    -0.08
    åĿIJåľ¨
    -0.08
    .parts
    -0.08
     нам
    -0.08
     Maurice
    -0.08
    æŁł
    -0.08
    çŃĮ
    -0.07
    POSITIVE LOGITS
    说è¿ĩ
    0.13
    ä¹ŁæĽ¾
    0.13
     elsewhere
    0.12
     earlier
    0.12
     ÑĢанее
    0.11
    å°Ī
    0.11
    æĽ¾ç»ı
    0.10
     previously
    0.10
    ä¸ĵéŨ
    0.10
    åģļè¿ĩ
    0.10
    Activations Density 0.170%

    No Known Activations