© 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. 49117
    Prev
    Next
    INDEX
    Explanations

    expressing gratitude

    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
    ero
    -0.09
    ering
    -0.09
    å®ĺåı¸
    -0.08
    ç§ijæķĻ
    -0.08
     tern
    -0.08
    åĢŁæѤ
    -0.08
    -0.08
    对ä»ĸ
    -0.08
    éĿĸ
    -0.08
    ers
    -0.07
    POSITIVE LOGITS
    HING
    0.11
    ÙĦاÙĨ
    0.11
    ä¹ĭæĥħ
    0.11
    LY
    0.10
    ness
    0.10
    fully
    0.10
    chandle
    0.09
    ctest
    0.09
    ì°¨
    0.09
    ive
    0.09
    Activations Density 0.005%

    No Known Activations