© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 975
    Prev
    Next
    INDEX
    Explanations

    customers and audience

    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
    azzo
    -0.24
     makeshift
    -0.24
    ugin
    -0.24
     counselling
    -0.23
     caution
    -0.23
     hardware
    -0.23
    umo
    -0.23
    çŃīä¸Ģæī¹
    -0.22
    Ñij
    -0.22
    .pointer
    -0.22
    POSITIVE LOGITS
    åıĹä¼Ĺ
    0.30
     audience
    0.30
    缮æłĩ
    0.28
    çŁ¥å·±
    0.28
    çĶ»åĥı
    0.27
    /target
    0.26
    人群
    0.25
    群ä½ĵ
    0.25
    /client
    0.25
    /custom
    0.25
    Activations Density 0.028%

    No Known Activations