© 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. 15720
    Prev
    Next
    INDEX
    Explanations

    punk rock bands and groups

    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
    ä¼Ļä¼´åħ³ç³»
    -0.19
    Ñıд
    -0.18
    æ§Ľ
    -0.18
    Ñħод
    -0.18
    -bodied
    -0.17
    orate
    -0.17
    ORIES
    -0.16
    lı
    -0.16
    ances
    -0.16
    æ²īéĩį
    -0.16
    POSITIVE LOGITS
    ified
    0.23
    ifying
    0.18
    ify
    0.18
    omite
    0.17
    ishly
    0.17
    åı£åı·
    0.17
     зÑĢениÑı
    0.17
    å°ıåŃIJ
    0.17
    iqu
    0.17
    åįģ足
    0.16
    Activations Density 0.002%

    No Known Activations