© 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. 23600
    Prev
    Next
    INDEX
    Explanations

    'll followed by a verb

    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
    ye
    -0.12
    ly
    -0.11
    HING
    -0.10
    ä½Ĩä¸įéĻIJäºİ
    -0.10
    ely
    -0.09
    esa
    -0.09
    ed
    -0.09
    dz
    -0.09
    es
    -0.09
    ASTE
    -0.09
    POSITIVE LOGITS
    çŀĦåĩĨ
    0.11
    vetica
    0.10
    ê¹IJ
    0.10
    ibrary
    0.10
    ä¸Ģåī¯
    0.10
     dozen
    0.10
    .itemView
    0.09
    terior
    0.09
    ä¸Ģå¦Ĥ
    0.09
    inois
    0.09
    Activations Density 0.019%

    No Known Activations