© 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. 9139
    Prev
    Next
    INDEX
    Explanations

    integer or programming type 'int'

    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
    ward
    -0.10
    weis
    -0.10
    ½
    -0.09
    ëģĶ
    -0.08
     gì
    -0.08
    asics
    -0.08
    ça
    -0.08
    ä¹Łåıªèĥ½
    -0.08
    hood
    -0.08
    trail
    -0.08
    POSITIVE LOGITS
    egers
    0.15
    ervals
    0.13
     /*<<<
    0.13
    egrate
    0.13
    egrity
    0.13
    ERRUPT
    0.13
    itial
    0.13
    ellij
    0.13
    errupted
    0.12
    ities
    0.12
    Activations Density 0.120%

    No Known Activations