© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 866
    Prev
    Next
    INDEX
    Explanations

    film director

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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»Ī端
    -0.27
    ç¼´è´¹
    -0.26
    å¸IJåı·
    -0.25
    åı£å¤´
    -0.24
    éģįåıĬ
    -0.24
    :///
    -0.24
    ä¸ĵåįĸ
    -0.23
    åıĤä¿Ŀ
    -0.23
    缸åħ³ä¿¡æģ¯
    -0.23
    mine
    -0.22
    POSITIVE LOGITS
    æī§å¯¼
    0.53
    导æ¼Ķ
    0.52
     films
    0.41
    æĭįæijĦ
    0.40
    çĶµå½±
    0.40
     director
    0.39
     filmmaker
    0.39
     film
    0.39
    film
    0.39
     Films
    0.38
    Activations Density 0.080%

    No Known Activations