© 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. 20655
    Prev
    Next
    INDEX
    Explanations

    over

    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
    rac
    -0.09
    沿çĿĢ
    -0.09
    odal
    -0.08
    sume
    -0.08
     overview
    -0.08
    ogl
    -0.08
    tent
    -0.08
    ÙĨب
    -0.08
    éĢı
    -0.08
    .dsl
    -0.08
    POSITIVE LOGITS
    çĺ¾
    0.12
    鼶ç¢İ
    0.10
    tures
    0.10
    å®īæ£Ģ
    0.10
    tones
    0.10
    rid
    0.10
    åħ¨æĸĩ
    0.10
     cogn
    0.09
    åĬ£
    0.09
    çģ
    0.09
    Activations Density 0.085%

    No Known Activations