© 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. 23824
    Prev
    Next
    INDEX
    Explanations

    planning and future actions

    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
    bih
    -0.08
    ota
    -0.08
    çĶ¨æīĭ
    -0.08
    说æĺİ
    -0.08
    æĢİä¹ĪåĬŀ
    -0.08
    OTA
    -0.08
     rect
    -0.08
    HAND
    -0.07
    atcher
    -0.07
    åįĪ
    -0.07
    POSITIVE LOGITS
    ãģĹãģ¦ãģĬãģı
    0.13
    è§ĦåĪĴ
    0.10
    è¿Īåĩº
    0.10
    çŁ¥å·±
    0.10
    _legal
    0.10
    å¼Ħ
    0.10
    æŃ¥éª¤
    0.09
    à¤ĺ
    0.09
    è¿Ļæł·åģļ
    0.09
    æĬĬèĩªå·±çļĦ
    0.09
    Activations Density 0.081%

    No Known Activations