© 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. 1937
    Prev
    Next
    INDEX
    Explanations

    preserved or preservation

    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
    èĢ³
    -0.10
    ipur
    -0.10
    iqu
    -0.10
    æµģ浪
    -0.10
    丼
    -0.09
    çķ¥
    -0.09
    ogan
    -0.09
    å·¡
    -0.09
    onces
    -0.09
    еÑĪ
    -0.09
    POSITIVE LOGITS
    ä¿ĿåŃĺ
    0.13
     preserved
    0.11
     preserving
    0.11
     preserves
    0.11
     preserve
    0.11
     preservation
    0.11
     Preservation
    0.10
    -im
    0.10
    å®Į好
    0.10
    åĩºåľŁ
    0.10
    Activations Density 0.051%

    No Known Activations