© 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. 2219
    Prev
    Next
    INDEX
    Explanations

    never will be

    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
    inc
    -0.27
    ptions
    -0.24
     lately
    -0.24
    æľĢè¿ij
    -0.24
     recently
    -0.23
    нÑĮ
    -0.23
    æľ¬èº«å°±
    -0.23
    fer
    -0.23
    Recent
    -0.22
    ined
    -0.22
    POSITIVE LOGITS
     forever
    0.35
     eternity
    0.30
     everlasting
    0.27
    æ°¸è¿ľ
    0.26
     Eternal
    0.26
     eternal
    0.26
    agnar
    0.25
    éļ¾å¿ĺ
    0.25
     Forever
    0.24
    æ°¸éģł
    0.24
    Activations Density 0.022%

    No Known Activations