© 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. 10818
    Prev
    Next
    INDEX
    Explanations

    able, ible, iable, urable suffixes

    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
    SCO
    -0.10
    äºĨèĩªå·±çļĦ
    -0.09
    çĸı
    -0.09
    è´¯
    -0.09
    OOM
    -0.08
    oom
    -0.08
    ä¼ĺè¶Ĭ
    -0.08
    äºĨä¸Ģåľº
    -0.08
    夫
    -0.08
    lett
    -0.08
    POSITIVE LOGITS
    able
    0.14
    izable
    0.11
    ible
    0.10
    itar
    0.10
    æĹ·
    0.09
    urable
    0.09
     easily
    0.09
    iable
    0.08
    _attrs
    0.08
    åĬłåĢį
    0.08
    Activations Density 0.209%

    No Known Activations