© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 16868
    Prev
    Next
    INDEX
    Explanations

    love stories, love again

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    olith
    -0.20
    woord
    -0.19
    ÑĢак
    -0.19
    ayar
    -0.18
    ANNEL
    -0.18
    velle
    -0.18
    ThreadId
    -0.18
    há»ķ
    -0.18
    usra
    -0.18
    hound
    -0.17
    POSITIVE LOGITS
    并åIJij
    0.21
     candidate
    0.20
    ductive
    0.19
    å¹¶åľ¨
    0.19
    åĢĻéĢī人
    0.18
    并对
    0.18
    并äºİ
    0.18
    Candidate
    0.18
    mong
    0.18
    èĪ¬çļĦ
    0.17
    Activations Density 0.008%

    No Known Activations