© 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. 57004
    Prev
    Next
    INDEX
    Explanations

    moving out of state

    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
    aggi
    -0.12
    çĥ¬
    -0.10
    hä
    -0.09
    ervo
    -0.09
    åŀ¢
    -0.08
    uais
    -0.08
    æĥ³åĪ°
    -0.08
     renew
    -0.08
    åĮ®ä¹ı
    -0.08
    æ¯ħ
    -0.08
    POSITIVE LOGITS
     elsewhere
    0.16
    åİ»äºĨ
    0.15
    åı¦æľī
    0.14
    åı¦è¡Į
    0.13
    åĪ¥ãģ®
    0.12
    åĪ«çļĦ
    0.12
    åı¦ä¸Ģ个
    0.11
     somewhere
    0.11
    éĤ£è¾¹
    0.11
    åħ¶ä»ĸ
    0.11
    Activations Density 0.085%

    No Known Activations