© 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. 3656
    Prev
    Next
    INDEX
    Explanations

    bachelor's degree

    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
    aji
    -0.09
    æļĤåģľ
    -0.09
    åŃ¦å®¶
    -0.09
    ÑĢÑıд
    -0.09
    олоÑģ
    -0.09
    elves
    -0.08
    fter
    -0.08
    kh
    -0.08
     Hang
    -0.08
    å§Ĭ
    -0.08
    POSITIVE LOGITS
    ×ķת
    0.09
     chá»ĭu
    0.09
    iasm
    0.09
    PLICATE
    0.09
     lẽ
    0.08
    èĽ®
    0.08
    ·¨
    0.08
    iliary
    0.08
    enal
    0.08
    achs
    0.08
    Activations Density 0.004%

    No Known Activations