© 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. 12152
    Prev
    Next
    INDEX
    Explanations

    pets, dogs, and animal ownership

    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
    åĩºå±Ģ
    -0.20
    æ¯ı次éĥ½
    -0.20
    诡å¼Ĥ
    -0.20
    âĺĵ
    -0.19
    è£ħå¤ĩåĪ¶éĢł
    -0.19
    çĹĺ
    -0.19
    èIJİ缩
    -0.19
    å«Įçĸij
    -0.19
    涵çĽĸ
    -0.18
    éĽī
    -0.18
    POSITIVE LOGITS
     pets
    0.26
    责任
    0.24
    éĻªä¼´
    0.23
    æłĩéħį
    0.23
    缸å¤Ħ
    0.23
    starter
    0.22
    ä¸ĢçĶŁ
    0.21
    责任å¿ĥ
    0.21
    ä¸Ģè¾ĪåŃIJ
    0.21
     lifetime
    0.20
    Activations Density 0.018%

    No Known Activations