© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12588
    Prev
    Next
    INDEX
    Explanations

    accordingly directed, compatible, needed

    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
    åĪ¹éĤ£
    -0.21
    鹤
    -0.18
    _COND
    -0.18
    æįĨ
    -0.18
    æĥ³çŁ¥éģĵ
    -0.18
     Realt
    -0.18
    iren
    -0.18
    iron
    -0.17
    assed
    -0.17
     ObjectType
    -0.17
    POSITIVE LOGITS
    èĩªè¡Į
    0.23
    depending
    0.22
     tùy
    0.21
    å¦Ĥä¸ĭ
    0.21
     accordingly
    0.20
    леж
    0.20
    èĩªä¸»
    0.20
     завиÑģиÑĤ
    0.20
    缸åºĶ
    0.20
     depending
    0.20
    Activations Density 0.170%

    No Known Activations