© 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. 15747
    Prev
    Next
    INDEX
    Explanations

    school district

    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
    çĪµå£«
    -0.20
    istic
    -0.20
     Ñģобой
    -0.19
    é¦ĸ缸
    -0.19
    åĽ½éĺ²éĥ¨
    -0.18
    InstanceOf
    -0.18
    absolute
    -0.18
    versions
    -0.17
    erness
    -0.17
    ç¾İåĨĽ
    -0.17
    POSITIVE LOGITS
    åĨħçļĦ
    0.25
    æīĢåľ¨åľ°
    0.24
    åĤį
    0.24
    -wide
    0.22
    wide
    0.21
    à¹ĥหà¸į
    0.20
    ALIGN
    0.19
    åĨħãģ®
    0.19
    åIJį称
    0.19
    atically
    0.18
    Activations Density 0.005%

    No Known Activations