© 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. 12872
    Prev
    Next
    INDEX
    Explanations

    DVD players, drives, version

    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
    chaft
    -0.20
    ally
    -0.18
    lessly
    -0.18
    ality
    -0.17
    oft
    -0.16
    ately
    -0.16
    ively
    -0.16
    idon
    -0.16
    æĭ¢
    -0.15
    ä¼Łå¤§
    -0.15
    POSITIVE LOGITS
    -ROM
    0.20
    ãĤ¸ãĥ§ãĥ³
    0.17
    æ´ĭèij±
    0.16
    รวม
    0.16
    çĵł
    0.16
    ä¹¾åĿ¤
    0.15
    èŁij
    0.15
    羣çIJĨ
    0.15
    AppComponent
    0.15
    wright
    0.15
    Activations Density 0.007%

    No Known Activations