© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8527
    Prev
    Next
    INDEX
    Explanations

    beautifully hand custom Italian prints

    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
    aje
    -0.09
    ophil
    -0.09
    istory
    -0.09
    éĥ¨åĪĨåĨħ容
    -0.09
    ·
    -0.09
    éĥ¨åĪĨåľ°åĮº
    -0.09
    åŁ
    -0.08
    å¾Ĺèµ·
    -0.08
    çīĪæĿĥå½ĴåİŁ
    -0.08
    à¤ł
    -0.08
    POSITIVE LOGITS
     Bord
    0.11
    çĸĻ
    0.11
    éºĹ
    0.09
    lest
    0.09
    꼬
    0.09
    ude
    0.08
    hower
    0.08
    heid
    0.08
    åĪĬçĻ»
    0.08
    akes
    0.08
    Activations Density 0.013%

    No Known Activations