© 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. 325
    Prev
    Next
    INDEX
    Explanations

    content moderation policies

    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
     planning
    -0.26
    èĦ¾èĥĥ
    -0.26
     intimately
    -0.25
    logan
    -0.25
     energ
    -0.25
    timing
    -0.25
    绣çŃ¹
    -0.25
    .timing
    -0.25
     consultants
    -0.24
    ogi
    -0.24
    POSITIVE LOGITS
     spam
    0.44
    è¿Ŀè§Ħ
    0.40
     flagged
    0.40
     censorship
    0.40
    å®¡æł¸
    0.38
    spam
    0.35
    éªļæī°
    0.34
    åı¯çĸij
    0.34
     banned
    0.33
     suspicious
    0.33
    Activations Density 0.157%

    No Known Activations