© 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. 27467
    Prev
    Next
    INDEX
    Explanations

    complete with

    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
    yles
    -0.12
    åIJĮæĹ¶ä¹Łæĺ¯
    -0.10
    以åıĬåħ¶ä»ĸ
    -0.10
    èį¸
    -0.10
    å¦Ĥæľīä¾µæĿĥ
    -0.09
    -dollar
    -0.09
    忤
    -0.09
    asher
    -0.09
    ä»Ģä¹Īäºĭæĥħ
    -0.09
     paraph
    -0.09
    POSITIVE LOGITS
    eor
    0.09
    缸åºĶ
    0.08
    æ°
    0.08
    æįį
    0.08
    çŃĸ
    0.08
     attendant
    0.08
    è¹ī
    0.08
    ETA
    0.08
    宵
    0.08
    ura
    0.08
    Activations Density 0.007%

    No Known Activations