© 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. 4825
    Prev
    Next
    INDEX
    Explanations

    packed with or full of

    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
    车åŃIJ
    -0.11
    æł·åŃIJ
    -0.10
    utan
    -0.10
    æīĭ表
    -0.09
     havoc
    -0.09
    çĮĽçĦ¶
    -0.09
    çģ¯åħī
    -0.09
    å¿ĥå¢ĥ
    -0.09
    çĥ¦èºģ
    -0.09
    ROUT
    -0.08
    POSITIVE LOGITS
    æµİ
    0.09
    çĻ»åľº
    0.09
    对èĩªå·±çļĦ
    0.09
    俨
    0.08
    淹没
    0.08
    ero
    0.08
    lyn
    0.08
    èħĨ
    0.08
    amy
    0.08
    DMA
    0.08
    Activations Density 0.004%

    No Known Activations