© 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. 63407
    Prev
    Next
    INDEX
    Explanations

    f-words and their suffixes

    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
     Kare
    -0.10
    OOM
    -0.09
    é¹Ħ
    -0.08
    åģļå®Į
    -0.08
    åħ¶ä¸Ńä¹ĭä¸Ģ
    -0.08
    ÙĪاس
    -0.08
    竦
    -0.08
    eous
    -0.08
    finance
    -0.08
    修订
    -0.08
    POSITIVE LOGITS
    emark
    0.09
    ẫn
    0.09
    subtype
    0.09
    atra
    0.09
    akra
    0.09
    诩
    0.08
    pedia
    0.08
    iras
    0.08
    urniture
    0.08
    å¡ij
    0.08
    Activations Density 0.033%

    No Known Activations