© 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. 18518
    Prev
    Next
    INDEX
    Explanations

    camping and campsites

    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
    oko
    -0.10
    éĹ²
    -0.10
     Gym
    -0.09
    åı¦
    -0.09
    浪漫
    -0.09
     perv
    -0.08
     earm
    -0.08
     lab
    -0.08
    acci
    -0.08
    è£ħåį¸
    -0.08
    POSITIVE LOGITS
    æľŁéĹ´
    0.10
     chù
    0.10
    eday
    0.10
    åİ»åĵªåĦ¿
    0.10
    æ¼ķ
    0.09
    ç»ĵæĿŁåIJİ
    0.09
    çŁ³åĮĸ
    0.09
    çªĴ
    0.09
    ers
    0.09
    rades
    0.09
    Activations Density 0.007%

    No Known Activations