© 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. 34947
    Prev
    Next
    INDEX
    Explanations

    back stack navigation

    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
    æ¯Ľ
    -0.10
    çĹĽ
    -0.10
    è¿Ļä¸Ģå¹´
    -0.10
    座
    -0.10
    éĻĦåĬł
    -0.09
    åIJĦè¡ĮåIJĦä¸ļ
    -0.09
    ë¹Ĺ
    -0.09
    èĬĹ
    -0.09
    sey
    -0.09
    _PAYLOAD
    -0.09
    POSITIVE LOGITS
    è¸ı
    0.09
    .bp
    0.09
    íĴĢ
    0.08
     иÑģÑĤоÑĢии
    0.08
    åĽŀåĪ°
    0.08
    åĨ¥
    0.08
    æ²īè¿·
    0.08
    BackStack
    0.08
    ç¥ŀéĢļ
    0.08
    éĢĥçĶŁ
    0.08
    Activations Density 0.355%

    No Known Activations