© 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. 684
    Prev
    Next
    INDEX
    Explanations

    scores, goals, touchdowns

    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
    anners
    -0.23
    ÑĮÑİ
    -0.23
    å¯Ĩ
    -0.23
     moderators
    -0.22
    regon
    -0.22
    ibs
    -0.22
    apers
    -0.21
    å·²ç»ıè¶ħè¿ĩ
    -0.21
     Bain
    -0.21
     lä
    -0.21
    POSITIVE LOGITS
     later
    0.27
    两次
    0.26
    ä¸Ģç¬Ķ
    0.25
    åħ¼ä»»
    0.24
    åĩłæ¬¡
    0.24
    åľ¨æ¸¸æĪıä¸Ń
    0.24
    WithValue
    0.24
    å¤ļ次
    0.23
     donated
    0.23
    æķij人
    0.23
    Activations Density 0.014%

    No Known Activations