© 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. 4324
    Prev
    Next
    INDEX
    Explanations

    changing or following 'the'

    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
    _requirements
    -0.09
    ÑĩÑĥ
    -0.09
    åħ¬çĶ¨
    -0.09
    ComputedStyle
    -0.09
     Ñģобой
    -0.09
    .Sys
    -0.09
     ÙĪØ°ÙĦÙĥ
    -0.08
     ÑģобÑģÑĤвенно
    -0.08
    å½¼
    -0.08
    HAND
    -0.08
    POSITIVE LOGITS
    ãģĻãĤĭãģ¨
    0.13
    ä½łå°±
    0.11
    ä¹ħäºĨ
    0.11
    å°±è¶Ĭ
    0.11
    ï¼ĮåĪĻ
    0.11
    å°±ä¼ļ
    0.10
    åĨįå¤ļ
    0.10
    íķĺë©´
    0.10
    ä»»ä½ķä¸Ģ个
    0.09
    å°±æľĥ
    0.09
    Activations Density 0.050%

    No Known Activations