© 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. 16606
    Prev
    Next
    INDEX
    Explanations

    .microsoft.com urls

    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
    å°ıå·§
    -0.23
    PyObject
    -0.20
    éľĨ
    -0.20
    nth
    -0.20
    æµģè¡ĮçļĦ
    -0.19
    chant
    -0.19
    çĭ¬æľīçļĦ
    -0.18
    ç¾¹
    -0.18
    çĶµåķĨå¹³åı°
    -0.18
    ilk
    -0.18
    POSITIVE LOGITS
    ency
    0.24
    mlink
    0.23
    ENCY
    0.23
    edy
    0.20
     Portions
    0.20
    encies
    0.19
    çķħ
    0.19
     Fog
    0.18
     Hunts
    0.18
    åı¦è¡Į
    0.18
    Activations Density 0.053%

    No Known Activations