© 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. 12963
    Prev
    Next
    INDEX
    Explanations

    used correctly

    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
    OPS
    -0.22
    ä¸ĢåĪĩéĥ½
    -0.21
    å»īä»·
    -0.20
    没è§ģè¿ĩ
    -0.19
    æĸ¹æĸ¹éĿ¢
    -0.19
    äºİæĺ¯æĪij
    -0.18
    並å°ĩ
    -0.18
    åİĨæĿ¥
    -0.18
    对ä¸įèµ·
    -0.18
    æĥ³åĪ°
    -0.18
    POSITIVE LOGITS
     properly
    0.31
     correctly
    0.25
     proper
    0.21
    proper
    0.21
    ä¸İåħ¶ä»ĸ
    0.21
     mụ
    0.21
    ÐľÐĺ
    0.20
    æŃ£ç¡®
    0.20
     alone
    0.20
     geg
    0.20
    Activations Density 0.135%

    No Known Activations