© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51355
    Prev
    Next
    INDEX
    Explanations

    Ashton Gate, Estonian, frighten

    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
    utter
    -0.11
    ish
    -0.10
    ings
    -0.10
    zzo
    -0.10
    inary
    -0.09
    ÙĪØ´
    -0.09
    avers
    -0.09
     monster
    -0.09
    ths
    -0.08
    esto
    -0.08
    POSITIVE LOGITS
    çĦ¶æĺ¯
    0.13
    ajan
    0.10
    aise
    0.10
    èĮĦ
    0.09
    IFIER
    0.09
    vÃŃ
    0.09
    trak
    0.09
    /or
    0.09
    oise
    0.09
    iaz
    0.09
    Activations Density 0.005%

    No Known Activations