© 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. 22939
    Prev
    Next
    INDEX
    Explanations

    pasta extruder

    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
    usher
    -0.11
    æłĭ
    -0.09
    OMPI
    -0.09
    èĸ
    -0.09
    verbs
    -0.09
    olin
    -0.08
    enas
    -0.08
    .RequestMethod
    -0.08
    _LOADING
    -0.08
    ç²īæľ«
    -0.08
    POSITIVE LOGITS
    åīĬåĩı
    0.11
    åĿļ飧
    0.11
    ä¸Ĭæ±½
    0.11
    æ²®
    0.10
    åĪĨ解
    0.10
    çIJĨ解åĴĮ
    0.10
    çĥĤ
    0.10
    çĨ
    0.10
    åĽĽäºĶ
    0.09
    åĴ¬
    0.09
    Activations Density 0.194%

    No Known Activations