© 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. 12172
    Prev
    Next
    INDEX
    Explanations

    brings to `.execute`

    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
    vale
    -0.19
    ecz
    -0.19
    elly
    -0.19
    çĶŁæŃ»
    -0.19
    QRST
    -0.18
    -ab
    -0.18
    ness
    -0.18
    evity
    -0.18
    bol
    -0.18
    ä¾Ŀ
    -0.18
    POSITIVE LOGITS
    åı¯éĢļè¿ĩ
    0.21
    åı¯åľ¨
    0.20
    ä¸Ģå¥Ĺ
    0.19
     shave
    0.19
    ãģijãģ°
    0.18
    è¡ħ
    0.17
    ä¸Ģç¢Ĺ
    0.17
    irie
    0.17
    iler
    0.17
    Assistant
    0.17
    Activations Density 0.001%

    No Known Activations