© 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. 11993
    Prev
    Next
    INDEX
    Explanations

    work out or work way

    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
    éĴº
    -0.18
    è·ijäºĨ
    -0.17
    è·ij
    -0.17
    éļıå¤Ħ
    -0.17
    并æĹł
    -0.17
    å®ģ
    -0.17
    /Object
    -0.17
    èĬ¬
    -0.17
    öff
    -0.16
    ä½ľæĪĺ
    -0.16
    POSITIVE LOGITS
    horse
    0.19
     havoc
    0.19
    -out
    0.19
    ed
    0.19
    ressed
    0.18
    around
    0.18
    loads
    0.18
    ESH
    0.18
    SAT
    0.17
     out
    0.17
    Activations Density 0.039%

    No Known Activations