© 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. 14471
    Prev
    Next
    INDEX
    Explanations

    Jac + following word (name, place, thing)

    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
    çŃĮ
    -0.19
    icket
    -0.19
    ação
    -0.18
    cher
    -0.17
    ÑģÑĤÑĢ
    -0.17
    æĮ¯åħ´
    -0.17
    iskey
    -0.16
    ality
    -0.16
    åĶ§
    -0.16
    ť
    -0.16
    POSITIVE LOGITS
    åĢij
    0.17
    度è¿ĩ
    0.17
    çĶŁæĢķ
    0.16
    STONE
    0.15
    VERT
    0.15
    Ùī
    0.15
    å©¿
    0.15
    ï¸ı
    0.15
    rd
    0.15
     Regards
    0.15
    Activations Density 0.004%

    No Known Activations