© 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. 19664
    Prev
    Next
    INDEX
    Explanations

    spa vacation

    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
    西è£ħ
    -0.09
    æµ·æ·Ģ
    -0.09
    è¿ŀéĶģ
    -0.09
    æīĵçĿĢ
    -0.09
    gary
    -0.08
    unday
    -0.08
     profile
    -0.08
    æĶ¹
    -0.08
     Plaza
    -0.08
     trapped
    -0.08
    POSITIVE LOGITS
    éĺ²èħIJ
    0.11
    æµģ转
    0.09
    çĸ«
    0.09
    èľļ
    0.09
    éĻĢ
    0.09
    åĹ½
    0.09
    åİŁè°ħ
    0.09
    è´¯éĢļ
    0.09
    令人
    0.09
    à¹ĥà¸Ī
    0.08
    Activations Density 0.014%

    No Known Activations