© 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. 54667
    Prev
    Next
    INDEX
    Explanations

    snapshot view or feature

    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
    usch
    -0.09
    åı¯æĢķçļĦ
    -0.09
     Congo
    -0.09
    abit
    -0.08
    ä¸įæĸŃåľ°
    -0.08
    olph
    -0.08
     lash
    -0.08
    缮
    -0.08
    iju
    -0.08
    brace
    -0.08
    POSITIVE LOGITS
    ting
    0.13
    ary
    0.09
    çį¾
    0.09
     snapshots
    0.09
    aneous
    0.09
     snapshot
    0.09
    éĥ
    0.09
    ãģĦãĤĭ
    0.09
    aneously
    0.09
    (snapshot
    0.08
    Activations Density 0.017%

    No Known Activations