© 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. 23333
    Prev
    Next
    INDEX
    Explanations

    follow/follower

    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
    orer
    -0.09
    çĹĺ
    -0.09
    çŃ¾
    -0.09
    çĽį
    -0.09
    åĨķ
    -0.08
     cushions
    -0.08
    obre
    -0.08
    FACE
    -0.08
    antom
    -0.08
    empre
    -0.08
    POSITIVE LOGITS
    earing
    0.09
    æĸĩåĮĸ产ä¸ļ
    0.08
    okit
    0.08
    å±ı
    0.08
    éĢīåĿĢ
    0.08
    åľ¨æĪijåĽ½
    0.08
    ç¡Ĵ
    0.08
     поÑĢÑıд
    0.08
    éĹªçĶµ
    0.08
    ght
    0.08
    Activations Density 0.018%

    No Known Activations