© 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. 27044
    Prev
    Next
    INDEX
    Explanations

    progression

    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
    çģ«çĦ°
    -0.12
    ampo
    -0.09
    reopen
    -0.09
    æ³¼
    -0.09
    eah
    -0.09
    åį³æŶ
    -0.09
    éĹªçĶµ
    -0.09
     Ade
    -0.08
    æ£ĺ
    -0.08
    æ¹Ľ
    -0.08
    POSITIVE LOGITS
     progression
    0.14
    æģ¶åĮĸ
    0.12
    åıijå±ķè¶ĭåĬ¿
    0.10
    è¿Ľå±ķæĥħåĨµ
    0.09
    åĬ¿
    0.09
    è¾ĥå¿«
    0.09
    åıijå±ķçļĦ
    0.09
    åĿ¡
    0.09
    éĻµ
    0.09
    åĭ¢
    0.09
    Activations Density 0.165%

    No Known Activations