© 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. 23674
    Prev
    Next
    INDEX
    Explanations

    highly regarded value

    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
    磨
    -0.09
    åĨĽåĽ¢
    -0.08
    ä¹ŁæĪIJ为
    -0.08
    ancell
    -0.08
    èĩªå¸¦
    -0.08
    arella
    -0.08
     bri
    -0.08
    çķ¸å½¢
    -0.08
    éĹ®éĹ®
    -0.08
     Passion
    -0.08
    POSITIVE LOGITS
    å¾Īé«ĺçļĦ
    0.11
    åı£å¤´
    0.10
    è§Ĩ为
    0.10
    å¾Īé«ĺ
    0.09
    yon
    0.09
    çľĭéĩį
    0.09
    好è¯Ħ
    0.09
    ä¿¡çĶ¨
    0.09
    è¿ĩé«ĺ
    0.09
    æŀģé«ĺ
    0.09
    Activations Density 0.036%

    No Known Activations