© 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. 62492
    Prev
    Next
    INDEX
    Explanations

    at the

    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
    尽头
    -0.10
    æ´»è·ĥ
    -0.09
    layers
    -0.08
    个交æĺĵ
    -0.08
    åħ¨åĽ½äººæ°ij
    -0.08
    çļĦè¡£æľį
    -0.08
    çİ®
    -0.08
    ìĭŃ
    -0.08
    Northern
    -0.08
    -fly
    -0.08
    POSITIVE LOGITS
    loor
    0.10
    森æŀĹåħ¬åĽŃ
    0.09
    eyer
    0.09
    åŀ«
    0.08
    åľ°äº§
    0.08
    çķĻå®ĪåĦ¿ç«¥
    0.08
    çŃīäºİ
    0.08
     Madagascar
    0.08
    æ©¡èĥ¶
    0.08
    paralle
    0.08
    Activations Density 0.016%

    No Known Activations