© 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. 885
    Prev
    Next
    INDEX
    Explanations

    legal citations (.Ct, .Dec)

    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
    寸
    -0.27
    çĶ¸
    -0.25
    çļĦç§ĺå¯Ĩ
    -0.25
     count
    -0.24
    çĶµåı°
    -0.23
    çļĦæĦŁæĥħ
    -0.23
    å¯Ĩçłģ
    -0.22
     quantities
    -0.22
    ä¸įçĶĺ
    -0.22
    æŶè£ħ
    -0.22
    POSITIVE LOGITS
    æµģæ°ĵ
    0.24
     fraternity
    0.23
    herits
    0.22
    ETCH
    0.22
    aits
    0.22
    rtl
    0.22
     thaw
    0.21
     USAGE
    0.21
     STRICT
    0.21
     Accessed
    0.21
    Activations Density 0.007%

    No Known Activations