© 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. 209
    Prev
    Next
    INDEX
    Explanations

    hacktarux

    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
     ccp
    -0.28
    uele
    -0.24
    é«ĺçŃīæķĻèĤ²
    -0.24
    /vnd
    -0.24
    목
    -0.23
    imetype
    -0.23
     Kaplan
    -0.23
    æĶ¶åıĹ
    -0.22
    NING
    -0.22
    ietf
    -0.22
    POSITIVE LOGITS
    鬼
    0.28
    éŃĤ
    0.27
     chorus
    0.27
     thr
    0.26
     trash
    0.26
     monsters
    0.26
     goose
    0.26
     beast
    0.26
     terror
    0.25
     candy
    0.25
    Activations Density 0.246%

    No Known Activations