© 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. 19205
    Prev
    Next
    INDEX
    Explanations

    travel lots and trips

    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
    çĻ»åľº
    -0.08
    Directed
    -0.08
    éķ¿å¯¿
    -0.08
    è¿IJä½ľ
    -0.08
    èij¬
    -0.08
    eker
    -0.08
    /il
    -0.08
     Directed
    -0.08
    ä»Ģ
    -0.08
    uko
    -0.08
    POSITIVE LOGITS
    ä¸Ģè¶Ł
    0.15
    éĢĶä¸Ń
    0.13
    缮çļĦåľ°
    0.11
    è¡Įç¨ĭ
    0.10
    æĹħç¨ĭ
    0.10
    è§Ĥåħī
    0.10
    âľĪ
    0.10
    è¶Ł
    0.10
    ðŁĴ¨
    0.10
    æĹħè¡Į
    0.10
    Activations Density 0.131%

    No Known Activations