© 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. 18437
    Prev
    Next
    INDEX
    Explanations

    landscaping and plants

    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
    è¾ľ
    -0.10
    é²ģ
    -0.09
    ocks
    -0.09
    åIJĮåѦ
    -0.08
    orks
    -0.08
     pinned
    -0.08
    ctors
    -0.08
    äºĭå®ŀ
    -0.08
    iedade
    -0.08
    hind
    -0.08
    POSITIVE LOGITS
    èĩªä¸»åĵģçīĮ
    0.11
    åĽŃæŀĹ
    0.11
    loth
    0.10
    èĭĹæľ¨
    0.10
    ç¾İåĮĸ
    0.09
    é²ľèĬ±
    0.09
    éĢł
    0.09
    æµĩ
    0.09
    jee
    0.09
    åħħå®ŀ
    0.09
    Activations Density 0.031%

    No Known Activations