© 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. 51691
    Prev
    Next
    INDEX
    Explanations

    displace, displaced, displacement

    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
    legs
    -0.11
    éĿ¢åŃIJ
    -0.10
    ctors
    -0.09
    cept
    -0.09
    APH
    -0.09
    keepers
    -0.09
    spiel
    -0.09
    èħ¿
    -0.08
    éģ¥æݧ
    -0.08
    ild
    -0.08
    POSITIVE LOGITS
     Ñģобой
    0.12
    èĩªå¦Ĥ
    0.09
    ément
    0.09
    ij
    0.09
    orf
    0.09
    ê²½ìłľ
    0.08
    acements
    0.08
     displ
    0.08
    arser
    0.08
    鼶ç¢İ
    0.08
    Activations Density 0.018%

    No Known Activations