© 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. 23712
    Prev
    Next
    INDEX
    Explanations

    times before

    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
    iani
    -0.12
    èĩ³ä»Ĭ
    -0.10
    çİ°ä»»
    -0.10
    èĪĨ
    -0.10
    ä»Ĭ天æĪij们
    -0.10
    çİ°æľī
    -0.10
    è¸Ĭè·ĥ
    -0.09
    LOGGER
    -0.09
    æĢĢ念
    -0.09
    PIP
    -0.09
    POSITIVE LOGITS
    æѤåīį
    0.18
    åľ¨æѤä¹ĭåīį
    0.17
     earlier
    0.17
     previous
    0.15
    åħĪåīį
    0.15
    åīįä¸Ģ天
    0.14
    åĪļåĪļ
    0.14
     Earlier
    0.14
     preceding
    0.14
     hadn
    0.14
    Activations Density 0.136%

    No Known Activations