© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2292
    Prev
    Next
    INDEX
    Explanations

    specialized abbreviations or technical terms

    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
    -resource
    -0.22
    -budget
    -0.22
    -imm
    -0.21
    -symbol
    -0.21
     recall
    -0.21
    .Inventory
    -0.20
     overloaded
    -0.20
    /views
    -0.20
    bru
    -0.20
    _sy
    -0.20
    POSITIVE LOGITS
    åıĪ称
    0.27
    è¿Ļ个åIJįåŃĹ
    0.24
    æĺ¯æľĢ
    0.24
    æĺ¯ä¸Ģ项
    0.24
    åłªç§°
    0.24
    çĶ±
    0.24
     essentially
    0.23
    ç¡®åĪĩ
    0.23
     basically
    0.23
    åħ±
    0.23
    Activations Density 0.166%

    No Known Activations