© 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. 12809
    Prev
    Next
    INDEX
    Explanations

    extension

    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
    istic
    -0.19
    å©¿
    -0.18
    shake
    -0.17
    æĽ²æĬĺ
    -0.17
    ertype
    -0.17
    INGS
    -0.17
    麾
    -0.17
    sheets
    -0.17
    侧ç»ĵæŀĦæĢ§
    -0.16
    ings
    -0.16
    POSITIVE LOGITS
    дей
    0.19
    ential
    0.18
    们
    0.17
    onian
    0.17
    豸
    0.17
    air
    0.17
    arp
    0.16
    iliary
    0.16
    isz
    0.16
    chron
    0.16
    Activations Density 0.017%

    No Known Activations