© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10003
    Prev
    Next
    INDEX
    Explanations

    distributing software under license terms

    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
    è°
    -0.09
    ness
    -0.09
    èĮ¬
    -0.09
    ä¸Ģéģį
    -0.08
    è¿Ļä¸ĢçĤ¹
    -0.08
    çľ¼éĩĮ
    -0.08
    linger
    -0.08
     ToDo
    -0.08
    çĩİ
    -0.08
    åħ¥
    -0.08
    POSITIVE LOGITS
    ively
    0.10
    ASE
    0.10
     Flyers
    0.10
    ally
    0.09
    ALLY
    0.09
    شب
    0.09
    ola
    0.09
    eper
    0.09
    ngo
    0.09
    ught
    0.09
    Activations Density 0.062%

    No Known Activations