© 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. 5215
    Prev
    Next
    INDEX
    Explanations

    alameda county or alamo city

    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
    éħIJ
    -0.10
    ä¸ĢéŨ
    -0.09
    otron
    -0.09
    ifo
    -0.09
    ounce
    -0.08
    amarin
    -0.08
    ivity
    -0.08
    åĴĮåľ°åĮº
    -0.08
    èĬĤ
    -0.08
    éĩľ
    -0.08
    POSITIVE LOGITS
    olib
    0.11
    èĨ³
    0.09
    TagName
    0.08
    éĻĦè¿ijçļĦ
    0.08
    urate
    0.08
    oha
    0.08
     Recorder
    0.08
    åĪĽ
    0.08
    Either
    0.08
    æŀľæłij
    0.08
    Activations Density 0.005%

    No Known Activations