© 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. 29817
    Prev
    Next
    INDEX
    Explanations

    general information

    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
    AREN
    -0.10
    åı±
    -0.09
    incess
    -0.09
    ional
    -0.09
    åĪ°åºķ
    -0.09
    顽
    -0.09
    缴æݥ影åĵį
    -0.09
    ä¸Ŀ毫
    -0.09
     Ade
    -0.09
    åħ¨é¢Ŀ
    -0.09
    POSITIVE LOGITS
    éĢļçĶ¨
    0.13
    /general
    0.12
    -purpose
    0.12
     general
    0.11
    .general
    0.10
    -general
    0.10
    general
    0.10
    anas
    0.09
     Rid
    0.08
    ä¾Ĩ說
    0.08
    Activations Density 0.200%

    No Known Activations