© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10057
    Prev
    Next
    INDEX
    Explanations

    Chen names

    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
    aire
    -0.12
    ãģĮãĤī
    -0.10
    edList
    -0.09
    ../../../
    -0.09
    CRM
    -0.09
    razil
    -0.09
     pname
    -0.09
    unos
    -0.08
     ÑģпÑĢав
    -0.08
    utch
    -0.08
    POSITIVE LOGITS
     Lux
    0.09
    elling
    0.09
    etz
    0.09
    /edit
    0.08
    ç½ijåıĭè¯Ħ论
    0.08
     fancy
    0.08
    arro
    0.08
    ffen
    0.08
     Copp
    0.08
    scription
    0.08
    Activations Density 0.035%

    No Known Activations