© 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. 14161
    Prev
    Next
    INDEX
    Explanations

    Manhattan

    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
    fully
    -0.18
    lessly
    -0.17
    atio
    -0.16
    çĺķ
    -0.16
    ounded
    -0.15
    grp
    -0.15
    èĮ§
    -0.15
     наг
    -0.15
    è´´å¿ĥ
    -0.15
    ëģĶ
    -0.15
    POSITIVE LOGITS
    ization
    0.23
    izer
    0.20
    że
    0.19
    izers
    0.19
    ities
    0.19
    ize
    0.18
    OLA
    0.18
    æŁĦ
    0.18
    ism
    0.18
    lit
    0.18
    Activations Density 0.005%

    No Known Activations