© 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. 33531
    Prev
    Next
    INDEX
    Explanations

    shrine of

    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
    -0.09
    åħ¶ä¸Ńä¹ĭä¸Ģ
    -0.09
    vanced
    -0.09
    éķ¿è¿ľ
    -0.09
    rocess
    -0.09
    ucci
    -0.08
    shift
    -0.08
    rics
    -0.08
    çijķ
    -0.08
    åĽłä¸ºå®ĥ
    -0.08
    POSITIVE LOGITS
    Ìģ
    0.10
    immel
    0.10
    ties
    0.09
    èĩ¾
    0.09
    Ñħод
    0.09
    ê¹IJ
    0.09
    ists
    0.09
    Ỽ
    0.09
    ä¸Ģ次次
    0.09
    ấn
    0.08
    Activations Density 0.004%

    No Known Activations