© 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. 22685
    Prev
    Next
    INDEX
    Explanations

    teaching

    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
    è¯ŀ
    -0.10
    bid
    -0.09
    adow
    -0.09
    å·½
    -0.09
    æijĽ
    -0.09
     Rt
    -0.09
    OME
    -0.09
    аÑİÑĤÑģÑı
    -0.08
    InputLabel
    -0.08
    人çī©
    -0.08
    POSITIVE LOGITS
    ä½łæĢİä¹Ī
    0.09
    ä»Ģä¹Īåı«
    0.09
    å¦Ĥä½ķåİ»
    0.09
    è¦ģçĤ¹
    0.09
    å¦Ĥä½ķ
    0.08
    .piece
    0.08
    æķĻãģĪ
    0.08
    åĬŁè¯¾
    0.08
    inos
    0.08
     lessons
    0.08
    Activations Density 0.036%

    No Known Activations