© 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. 10104
    Prev
    Next
    INDEX
    Explanations

    LTE, GSM, HTC, AT&T

    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
    ric
    -0.10
    itary
    -0.09
    richt
    -0.09
    IMUM
    -0.09
    cept
    -0.09
    åĵĪåĵĪ
    -0.08
    ми
    -0.08
    fur
    -0.08
    ockets
    -0.08
    æŀ«
    -0.08
    POSITIVE LOGITS
    çĶ¥
    0.10
    æ°ijæĦı
    0.09
    çĻ»å±±
    0.09
    çıij
    0.08
    éĵİ
    0.08
    ija
    0.08
    sis
    0.08
    ATCH
    0.08
    alia
    0.08
     Pret
    0.08
    Activations Density 0.009%

    No Known Activations