© 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. 54174
    Prev
    Next
    INDEX
    Explanations

    Sab prefix

    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
    soever
    -0.10
    amp
    -0.10
    uns
    -0.09
    åĶ±çīĩ
    -0.08
    erk
    -0.08
    ãģ¹ãģį
    -0.08
    olon
    -0.08
    аÑĢи
    -0.08
     комнаÑĤ
    -0.08
    umm
    -0.08
    POSITIVE LOGITS
     Ñģобой
    0.11
    deen
    0.10
    çĸĻ
    0.10
    ãģĦãģĨ
    0.10
    onian
    0.10
    ipl
    0.10
    黾
    0.09
    ðŁı»
    0.09
    lah
    0.09
    ÑİÑģÑĮ
    0.08
    Activations Density 0.013%

    No Known Activations