© 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. 11902
    Prev
    Next
    INDEX
    Explanations

    conservatism and legitimacy

    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
    åŃ¦æľ¯
    -0.24
    огÑĢаÑĦ
    -0.20
    èµ°åĩº
    -0.20
     Claw
    -0.19
    ä¸ļåĨħ
    -0.19
    าว
    -0.19
    åĨ²
    -0.19
    绿è±Ĩ
    -0.18
    PACK
    -0.18
    @m
    -0.18
    POSITIVE LOGITS
    秩åºı
    0.36
     order
    0.28
    稳å®ļ
    0.26
     stability
    0.26
    æĶ¿æĿĥ
    0.25
    ç¨³åĽº
    0.25
    åĪ¶åº¦
    0.25
     Stability
    0.24
    æŧ
    0.23
    å®īå®ļ
    0.23
    Activations Density 0.049%

    No Known Activations