© 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. 13033
    Prev
    Next
    INDEX
    Explanations

    moving and relocation

    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
    ç»ĩ
    -0.23
    ç»°
    -0.22
    åĺŁ
    -0.21
    åı£è¯Ń
    -0.21
    abh
    -0.21
    èĪĮ
    -0.20
    è·Łè¸ª
    -0.20
    éĽİ
    -0.20
    çĸ½
    -0.20
    å¾ĹçŁ¥
    -0.20
    POSITIVE LOGITS
    æķ´çIJĨ
    0.41
    æ¸ħçIJĨ
    0.38
    æIJ¬å®¶
    0.35
    æIJ¬è¿ģ
    0.33
     belongings
    0.29
    æĶ¶æĭ¾
    0.29
    æIJ¬
    0.26
    è¿ģ移
    0.26
     cleanup
    0.26
    çī©åĵģ
    0.25
    Activations Density 0.104%

    No Known Activations