© 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. 39933
    Prev
    Next
    INDEX
    Explanations

    NOT or FREE followed by context

    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
    lam
    -0.08
    -être
    -0.08
    manship
    -0.08
    otional
    -0.08
     EGL
    -0.08
    OOK
    -0.07
    LAN
    -0.07
    /her
    -0.07
     Hood
    -0.07
    åīįæīĢ
    -0.07
    POSITIVE LOGITS
    /OR
    0.13
    dden
    0.10
    _PTR
    0.10
    ropol
    0.10
    ÙĬص
    0.09
    üst
    0.09
    ãģŁãĤģãģ«
    0.09
    Ñľ
    0.09
    èİİ
    0.09
    ой
    0.09
    Activations Density 0.133%

    No Known Activations