© 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. 54447
    Prev
    Next
    INDEX
    Explanations

    beef

    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
    .CreateInstance
    -0.10
    æľ½
    -0.09
    à¸ģารà¸Ĺำà¸ĩาà¸Ļ
    -0.08
    ï¬Ħ
    -0.08
    lename
    -0.08
    osos
    -0.08
    emics
    -0.08
    éģĺ
    -0.08
    stoff
    -0.08
    éĩİ
    -0.08
    POSITIVE LOGITS
    lijk
    0.10
    ä»Ģä¹ĪåİŁåĽł
    0.10
     cattle
    0.10
    aight
    0.09
    èĭ´
    0.09
    ä¹³ä¸ļ
    0.09
    æѤåĪ»
    0.09
    é»į
    0.09
    inite
    0.09
    ause
    0.08
    Activations Density 0.007%

    No Known Activations