© 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. 56896
    Prev
    Next
    INDEX
    Explanations

    Blitz, Fritz, Berry, Blatz

    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
    èŁł
    -0.08
    档次
    -0.08
    nt
    -0.08
    apist
    -0.08
    vice
    -0.08
    zelf
    -0.08
    www
    -0.08
    ãģ©ãģĵãĤį
    -0.08
    è¾¾å°Ķ
    -0.08
    lessly
    -0.08
    POSITIVE LOGITS
    peed
    0.09
    ens
    0.09
    kul
    0.09
    buster
    0.09
    IFY
    0.08
    ness
    0.08
    uja
    0.08
     شاÙħÙĦ
    0.08
    tings
    0.08
    rix
    0.08
    Activations Density 0.001%

    No Known Activations