© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 49358
    Prev
    Next
    INDEX
    Explanations

    spooky movies or organizations

    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
    è¾ĺ
    -0.09
    çĶŁæľº
    -0.09
    ocale
    -0.08
    croft
    -0.08
    ugin
    -0.08
    é¢Ĭ
    -0.08
    mitter
    -0.08
    aurus
    -0.08
    è¾ĥ强çļĦ
    -0.08
    uzzer
    -0.07
    POSITIVE LOGITS
    adel
    0.10
    éŃį
    0.10
    å·¦æīĭ
    0.10
    sville
    0.09
    桧
    0.09
    tar
    0.09
    åħ°èĬ±
    0.09
    oni
    0.09
    iness
    0.09
    ier
    0.08
    Activations Density 0.002%

    No Known Activations