© 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. 7107
    Prev
    Next
    INDEX
    Explanations

    places and regions

    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
    ê»ı
    -0.09
    èĬĴæŀľ
    -0.09
    announce
    -0.09
    åºł
    -0.09
    رت
    -0.09
    æ·Ģ
    -0.08
    ìľ¼
    -0.08
    аÑĤа
    -0.08
     ven
    -0.08
    SqlServer
    -0.08
    POSITIVE LOGITS
    sson
    0.10
    sey
    0.09
    åķī
    0.09
    rial
    0.09
    amen
    0.08
    çģ«çĥ§
    0.08
     intermediary
    0.08
     bev
    0.08
    izard
    0.08
    çĪ±å°Ķåħ°
    0.08
    Activations Density 0.020%

    No Known Activations