© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15116
    Prev
    Next
    INDEX
    Explanations

    humans and mammals

    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
    è·ŁæĪij
    -0.21
    åĻª
    -0.20
    oke
    -0.20
    ernote
    -0.19
    æķijæµİ
    -0.19
    orst
    -0.18
     WCS
    -0.18
    izzard
    -0.18
    ä½łéľĢè¦ģ
    -0.18
     Redistribution
    -0.17
    POSITIVE LOGITS
    -readable
    0.22
    -centered
    0.19
    latex
    0.19
    -centric
    0.19
     diseases
    0.17
    translate
    0.17
     ÑģÑĤол
    0.17
     наÑħод
    0.17
    çĸ¾çĹħ
    0.17
    oids
    0.17
    Activations Density 0.119%

    No Known Activations