© 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. 11089
    Prev
    Next
    INDEX
    Explanations

    blue

    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
    ally
    -0.16
    itory
    -0.16
    nos
    -0.16
     виде
    -0.15
    uted
    -0.15
    ments
    -0.15
    ²
    -0.15
    iveness
    -0.14
    éĻIJãĤĬ
    -0.14
    nb
    -0.14
    POSITIVE LOGITS
    prints
    0.24
    berry
    0.23
    -collar
    0.21
    leaf
    0.19
    headed
    0.18
    eing
    0.18
    0.18
    -green
    0.18
    -grey
    0.18
    æł·çļĦ
    0.18
    Activations Density 0.023%

    No Known Activations