© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 8599
    Prev
    Next
    INDEX
    Explanations

    Kerala

    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
     lecturer
    -0.09
    .cam
    -0.09
    ooth
    -0.08
    SMS
    -0.08
    çľ¼çIJĥ
    -0.08
    OMATIC
    -0.08
    udent
    -0.08
    èĥŃ
    -0.08
    instanc
    -0.08
    åł
    -0.08
    POSITIVE LOGITS
     Portland
    0.11
    Portland
    0.11
    Oregon
    0.10
     Kerala
    0.10
    嵬
    0.09
    LOS
    0.09
    éĻķ
    0.09
    thy
    0.09
     gps
    0.09
     Oregon
    0.09
    Activations Density 0.204%

    No Known Activations