© 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. 52944
    Prev
    Next
    INDEX
    Explanations

    universities and colleges

    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
    缨
    -0.10
     Metro
    -0.09
    çĤĻ
    -0.09
     hk
    -0.08
    çĥŃéŨ
    -0.08
    çł´
    -0.08
     Duch
    -0.08
    머
    -0.08
    åIJ¸åıĸ
    -0.08
    å¼Ģå°ģ
    -0.08
    POSITIVE LOGITS
     sourceMapping
    0.10
     Orr
    0.09
    __/
    0.09
     THROW
    0.09
    /libs
    0.09
    gMaps
    0.08
    .ease
    0.08
     Surg
    0.08
     Advis
    0.08
    .CONNECT
    0.08
    Activations Density 0.044%

    No Known Activations