© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10289
    Prev
    Next
    INDEX
    Explanations

    Po followed by variety or names

    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
    ëŀij
    -0.10
    妹
    -0.09
    ../../../
    -0.09
    çħĮ
    -0.09
    rag
    -0.09
    inz
    -0.08
     quần
    -0.08
    terror
    -0.08
    __('
    -0.08
    å¤ĦåĪĨ
    -0.08
    POSITIVE LOGITS
    èĸ®
    0.11
    entially
    0.11
    plr
    0.11
    verty
    0.10
     laure
    0.10
    ocks
    0.09
    gers
    0.09
    è¿Ļåħ¶ä¸Ń
    0.09
    etry
    0.09
    enheim
    0.09
    Activations Density 0.031%

    No Known Activations