© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 37008
    Prev
    Next
    INDEX
    Explanations

    investment fund or close

    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
    /testing
    -0.09
    enn
    -0.09
    Ñĥв
    -0.09
    ç¥ģ
    -0.08
    oya
    -0.08
    çĤĴä½ľ
    -0.08
    éĢĢä¼ij
    -0.08
    笪
    -0.08
    otten
    -0.08
     Bale
    -0.08
    POSITIVE LOGITS
     comb
    0.08
    AccessType
    0.08
    igel
    0.08
    éĢĤåIJĪèĩªå·±
    0.08
    æijĪ
    0.08
    çĥĥ
    0.08
    æŃ£èĥ½éĩı
    0.08
    .linalg
    0.08
    .cms
    0.08
     Ital
    0.08
    Activations Density 0.046%

    No Known Activations