© 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. 20583
    Prev
    Next
    INDEX
    Explanations

    Jane followed by a surname

    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
    ally
    -0.12
    sWith
    -0.11
    ingly
    -0.11
    atic
    -0.11
    ย
    -0.10
    éĩįéĩį
    -0.10
    人éĢł
    -0.10
    ме
    -0.10
    rix
    -0.10
    aurus
    -0.10
    POSITIVE LOGITS
    istic
    0.12
    bones
    0.12
     Doe
    0.10
    té
    0.10
    é²·
    0.10
    ãģªãĤĭ
    0.10
     minded
    0.09
    åĽŀé¦ĸ
    0.09
    keeping
    0.09
    brush
    0.09
    Activations Density 0.008%

    No Known Activations