© 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. 16488
    Prev
    Next
    INDEX
    Explanations

    sourceforge.net projects

    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
    å®īå®ģ
    -0.22
    orde
    -0.21
    earer
    -0.20
     оÑĩеÑĢ
    -0.19
    ali
    -0.19
    æķĪæŀľ
    -0.19
     prose
    -0.18
    ori
    -0.18
    çħ½
    -0.18
    -effect
    -0.18
    POSITIVE LOGITS
    ãĥĹãĥŃãĤ¸ãĤ§ãĤ¯ãĥĪ
    0.28
     project
    0.26
    é¡¹çĽ®
    0.26
     пÑĢоекÑĤ
    0.25
     projects
    0.24
    æīĺ管
    0.23
    è¯¥é¡¹çĽ®
    0.23
     proyectos
    0.22
    /Open
    0.21
    _projects
    0.21
    Activations Density 0.286%

    No Known Activations