© 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. 57364
    Prev
    Next
    INDEX
    Explanations

    prepared for

    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
    å·§
    -0.11
    cob
    -0.10
    utan
    -0.10
    å½°
    -0.09
    转åıij
    -0.09
    åĮı
    -0.09
    æī§
    -0.09
     desta
    -0.09
    åĸĦäºİ
    -0.09
     bleeding
    -0.09
    POSITIVE LOGITS
    åĩĨå¤ĩ
    0.10
     prepares
    0.10
    æºĸåĤĻ
    0.10
    åħ»
    0.09
     preparing
    0.09
    使åij½
    0.09
    .defer
    0.09
    æ¯Ľå·¾
    0.09
     prepare
    0.08
    _prepare
    0.08
    Activations Density 0.028%

    No Known Activations