© 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. 16636
    Prev
    Next
    INDEX
    Explanations

    neo-

    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
    ings
    -0.24
    INGS
    -0.21
    boo
    -0.19
     forth
    -0.18
    ANCE
    -0.18
    annya
    -0.18
    äºĨä¸Ģåı£
    -0.18
    ance
    -0.17
    way
    -0.17
    ged
    -0.17
    POSITIVE LOGITS
    erior
    0.19
    bie
    0.18
    ç¹ģèį£
    0.17
    /new
    0.17
    utory
    0.17
    å¼¯æĽ²
    0.17
    axies
    0.17
    请大家
    0.17
    -era
    0.16
    thalm
    0.16
    Activations Density 0.022%

    No Known Activations