© 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. 11138
    Prev
    Next
    INDEX
    Explanations

    limit or restrict

    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
    失
    -0.10
    unity
    -0.09
    estate
    -0.09
    uno
    -0.09
    úa
    -0.08
    .Documents
    -0.08
    à¸Ľà¸£à¸°à¸Īำ
    -0.08
    åĪ»
    -0.08
    ee
    -0.08
    oggle
    -0.08
    POSITIVE LOGITS
    combe
    0.10
    ToOne
    0.09
    å±ĢéĻIJäºİ
    0.09
    æݥ触
    0.09
    åıĹä¼Ĺ
    0.08
    人们对
    0.08
    æݥ触åĪ°
    0.08
     circ
    0.08
    éĢļå¾Ģ
    0.08
    æľ¬èĥ½
    0.08
    Activations Density 0.027%

    No Known Activations