© 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. 53794
    Prev
    Next
    INDEX
    Explanations

    relative or associate

    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
    èĢķ
    -0.09
    ers
    -0.09
    éŀį
    -0.08
    快讯
    -0.08
    æĸ°äºº
    -0.08
    åħ¶ä¸Ńä¹ĭä¸Ģ
    -0.08
    imers
    -0.08
    inton
    -0.08
    emy
    -0.08
    former
    -0.08
    POSITIVE LOGITS
    å§Ĭ妹
    0.17
     sister
    0.15
    å§IJ妹
    0.15
    åħĦå¼Ł
    0.13
     sisters
    0.11
     Sister
    0.11
    å¼Ł
    0.10
     brothers
    0.09
    _sibling
    0.09
    Sibling
    0.09
    Activations Density 0.027%

    No Known Activations