© 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. 7740
    Prev
    Next
    INDEX
    Explanations

    financial gain, control, or knowledge

    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
    gel
    -0.13
    è´¯
    -0.11
     же
    -0.10
    acin
    -0.09
    ture
    -0.09
    ä¸ĵ人
    -0.09
    岿
    -0.08
    gun
    -0.08
    illation
    -0.08
    inary
    -0.08
    POSITIVE LOGITS
    fully
    0.13
    Ñĩив
    0.12
    nable
    0.12
    çĽĬ
    0.11
    eous
    0.10
    keepers
    0.09
    OrUpdate
    0.09
    æĢ§çĸ¾çĹħ
    0.09
    ithe
    0.09
    sett
    0.09
    Activations Density 0.029%

    No Known Activations