© 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. 13193
    Prev
    Next
    INDEX
    Explanations

    18 years

    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
    alité
    -0.20
    åħĭæľį
    -0.20
    rna
    -0.19
    æĸ¯é¡¿
    -0.19
    楹
    -0.19
    hlen
    -0.18
    è°Ĺ
    -0.18
    åĬ¿å¤´
    -0.18
    ÑĩÑĮ
    -0.17
     sourceMapping
    -0.17
    POSITIVE LOGITS
    åIJİçļĦ
    0.22
    éĽī
    0.21
    绡
    0.21
    +
    0.20
     shooter
    0.20
    çĵ®
    0.19
     liberty
    0.18
     age
    0.18
     mes
    0.18
    满äºĨ
    0.17
    Activations Density 0.013%

    No Known Activations