© 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. 55224
    Prev
    Next
    INDEX
    Explanations

    inhibitory, regulatory, or effect-related endings

    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
    åĮĸè¿Ľç¨ĭ
    -0.09
    æĮīæŶ
    -0.09
    çĪ°
    -0.09
    ization
    -0.09
    èĭij
    -0.09
    äºĨä¸Ģåľº
    -0.08
    äºĨä¸Ģ个
    -0.08
     admir
    -0.08
    åĮĸ
    -0.08
    éŀ«
    -0.08
    POSITIVE LOGITS
     ÙĪاÙĦت
    0.09
    åĽ½èµĦ
    0.09
    çĭĤ
    0.09
    èĩªå¦Ĥ
    0.09
    uming
    0.09
     Shank
    0.09
     ×ij׼
    0.09
    欲
    0.09
    ulo
    0.09
    ive
    0.09
    Activations Density 0.260%

    No Known Activations