© 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. 11525
    Prev
    Next
    INDEX
    Explanations

    select certain

    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
    rees
    -0.09
    åĨ³ä¸į
    -0.08
    å¦Ĥæŀľè¯´
    -0.08
    çĿ¬
    -0.08
    rip
    -0.08
     scram
    -0.08
    说å®ŀè¯Ŀ
    -0.08
    æĢ»çļĦ
    -0.07
    åįģä½³
    -0.07
     patrons
    -0.07
    POSITIVE LOGITS
    eci
    0.10
    çľģ份
    0.09
    ucus
    0.09
    æŶåĪ»
    0.09
    ennen
    0.09
    å·²ä¹ħçļĦ
    0.09
    0.09
     jub
    0.09
    аÑĢам
    0.09
    ITE
    0.09
    Activations Density 0.010%

    No Known Activations