© 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. 33598
    Prev
    Next
    INDEX
    Explanations

    trout rivers

    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
    满äºĨ
    -0.10
    éĢĢè´§
    -0.09
    pile
    -0.09
    itten
    -0.09
    YLE
    -0.09
    åģļå¾Ĺ
    -0.09
    æĶ¾å¿ĥ
    -0.09
    ense
    -0.09
    illator
    -0.09
    lli
    -0.08
    POSITIVE LOGITS
    çī¹æĿĥ
    0.10
    路段
    0.10
    è¿Ļ段
    0.09
    çĶŁåij½çļĦ
    0.08
    umph
    0.08
    åĨµä¸Ķ
    0.08
    æµģåĬ¨
    0.08
     Hoover
    0.08
    sections
    0.08
    亲çĪ±
    0.08
    Activations Density 0.089%

    No Known Activations