© 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. 11426
    Prev
    Next
    INDEX
    Explanations

    New York, London, University

    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
    ائÙĦ
    -0.09
    åıŁ
    -0.09
    åĽłåľ°
    -0.09
    æĦıè§ģåıįé¦Ī
    -0.09
    ına
    -0.09
    é¦ĸéĥ½
    -0.09
    riority
    -0.09
    çľģæķĻèĤ²
    -0.08
    ikers
    -0.08
    浸
    -0.08
    POSITIVE LOGITS
    触
    0.09
    дов
    0.09
    横
    0.08
    çĪ±ä¸Ĭ
    0.08
     Coun
    0.08
     bounce
    0.08
    çľī
    0.08
    éĽ¾
    0.08
    转åıĺ
    0.08
     contr
    0.07
    Activations Density 0.010%

    No Known Activations