© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9527
    Prev
    Next
    INDEX
    Explanations

    testing phantom

    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
    éĵŃ
    -0.09
    lexport
    -0.09
    æĺ§
    -0.09
     Lawson
    -0.08
    çĪ±å¥ĩ
    -0.08
    æĭľ
    -0.08
    æ°Ķ温
    -0.08
     ihtiy
    -0.08
    toa
    -0.08
    .mass
    -0.08
    POSITIVE LOGITS
    模çī¹
    0.15
    模æĭŁ
    0.14
    ä»¿çľŁ
    0.11
    模åŀĭ
    0.11
     models
    0.10
    simulate
    0.10
    鹿
    0.10
     model
    0.09
     simulate
    0.09
    缴éĢļ车
    0.09
    Activations Density 0.320%

    No Known Activations