© 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. 55028
    Prev
    Next
    INDEX
    Explanations

    color names and values

    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
    åij¨äºĶ
    -0.09
    ç«ĭãģ¦
    -0.09
    å¾ģæ±Ĥ
    -0.09
    åij¨åĽĽ
    -0.08
    åIJ¹
    -0.08
    èIJ½
    -0.08
    红线
    -0.08
    åį·
    -0.08
    ftype
    -0.08
    嵯
    -0.08
    POSITIVE LOGITS
    èī²
    0.11
    èī²å½©
    0.10
    è°ĥéħį
    0.10
    éł»éģĵ
    0.09
    姹
    0.09
     mixing
    0.09
    çĬĦ
    0.09
    æł¼æŀĹ
    0.09
    æĴĩ
    0.09
     undert
    0.09
    Activations Density 0.151%

    No Known Activations