© 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. 56465
    Prev
    Next
    INDEX
    Explanations

    access to networks and data

    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
    åįİ缼
    -0.11
    éĢĿ
    -0.10
    驾
    -0.10
    eterminate
    -0.09
    ç¥ļ
    -0.08
    å®īçĦ¶
    -0.08
    æ¡£
    -0.08
    ysz
    -0.08
    çĴł
    -0.08
    åı¯æĥ³èĢĮçŁ¥
    -0.08
    POSITIVE LOGITS
    åĪ°è¾¾
    0.10
    RET
    0.10
    æĬµè¾¾
    0.10
    çļĦè·Ŀ离
    0.09
    ç»ĪçĤ¹
    0.09
    èİ·å¾ĹæĦŁ
    0.09
     nale
    0.09
    .TO
    0.09
     finishing
    0.09
    çłĶ究æīĢ
    0.09
    Activations Density 0.078%

    No Known Activations