© 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. 2149
    Prev
    Next
    INDEX
    Explanations

    interchangeably, difference, overlap, nonexistent

    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
    çĭ¬èĩª
    -0.29
    为空
    -0.25
    çĭ¬
    -0.23
    éģ¿å¼Ģ
    -0.22
    è§Ħç¨ĭ
    -0.22
    heard
    -0.22
     Basis
    -0.21
    ania
    -0.21
     separately
    -0.21
    èIJ½ä¸ĭ
    -0.21
    POSITIVE LOGITS
    èŀį为ä¸Ģä½ĵ
    0.35
    èŀįåIJĪåıijå±ķ
    0.35
    èŀį
    0.33
    èŀįåIJĪ
    0.31
     merge
    0.30
    深度èŀįåIJĪ
    0.30
    模ç³Ĭ
    0.30
     merges
    0.29
     merging
    0.28
    åIJĪ并
    0.27
    Activations Density 0.151%

    No Known Activations