© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 186
    Prev
    Next
    INDEX
    Explanations

    paranoia, delusions, schizophrenia

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    çīĮ
    -0.20
     pena
    -0.20
    åıĤ
    -0.20
     bid
    -0.20
    arbeit
    -0.20
    /controller
    -0.19
    èįīåľ°
    -0.19
    tee
    -0.19
    åģļåĪ°
    -0.19
    ç¥Ŀ
    -0.19
    POSITIVE LOGITS
     conspir
    0.24
     paranoid
    0.23
    说æĪij
    0.23
     schizophren
    0.22
    NSS
    0.22
    çĮĸ
    0.22
     Conspiracy
    0.21
    vfs
    0.21
    ingly
    0.21
    åħ®
    0.21
    Activations Density 0.003%

    No Known Activations