© 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. 57928
    Prev
    Next
    INDEX
    Explanations

    exit status or code

    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
    åĩºèº«
    -0.11
    kers
    -0.10
    西æ¹ĸ
    -0.10
    ä¸Ģå¤ľ
    -0.09
    åħĪè¿ĽçļĦ
    -0.09
    hind
    -0.09
    ÑĥÑĤ
    -0.09
    对ä¸įèµ·
    -0.09
     Chocolate
    -0.09
    OCI
    -0.09
    POSITIVE LOGITS
    ting
    0.14
    ters
    0.13
    .Exit
    0.10
    TING
    0.10
    ential
    0.10
    (exit
    0.10
    YPE
    0.10
    ÑıÑī
    0.10
    (EXIT
    0.10
    prising
    0.10
    Activations Density 0.022%

    No Known Activations