© 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. 34365
    Prev
    Next
    INDEX
    Explanations

    project management software

    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
     Cove
    -0.11
    aea
    -0.09
    aic
    -0.09
    æ¯Ĵ
    -0.08
    Susp
    -0.08
    bler
    -0.08
    CID
    -0.08
    ноÑģ
    -0.08
    _ASYNC
    -0.08
    æĤłæĤł
    -0.08
    POSITIVE LOGITS
    åĬŀäºĭ
    0.11
    зÑĥ
    0.10
    ä¸Ĭåīį
    0.10
     Reform
    0.09
    íľĺ
    0.09
    ä»Ħ
    0.09
    绫
    0.09
    漫çĶ»
    0.09
    è¯Ŀ说
    0.08
     reform
    0.08
    Activations Density 0.110%

    No Known Activations