© 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. 2591
    Prev
    Next
    INDEX
    Explanations

    catch up with

    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
     sÃłn
    -0.09
    oplay
    -0.08
    åĿĩåĮĢ
    -0.08
    ä½ķå¤Ħ
    -0.08
    ocre
    -0.08
    squ
    -0.08
    åıĬæŶ
    -0.08
     Tim
    -0.08
    hood
    -0.08
    ARING
    -0.08
    POSITIVE LOGITS
    OrCreate
    0.12
    åĻľ
    0.10
     bele
    0.09
    輩
    0.09
    å¹´æĿ¥
    0.09
    侪
    0.09
    mere
    0.09
    åīįèĢħ
    0.09
     DAMAGES
    0.09
    ingly
    0.09
    Activations Density 0.006%

    No Known Activations