© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12263
    Prev
    Next
    INDEX
    Explanations

    use of

    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±
    -0.21
    åĩºå¤Ħ
    -0.19
    æĺı
    -0.19
    å·§å¦Ļ
    -0.18
    æªĶ
    -0.18
    ÑĩаÑĤ
    -0.18
    åIJĪéĢĤ
    -0.18
    çĭĻåĩ»
    -0.18
    级
    -0.17
    çĶŁåij½åĬĽ
    -0.17
    POSITIVE LOGITS
    ancode
    0.21
    reno
    0.21
    æİ¥åħ¥
    0.21
    æĦīå¿«
    0.19
    èļģ
    0.19
    ufe
    0.18
    heimer
    0.18
    .assertAlmostEqual
    0.18
    gue
    0.18
    èĽ²
    0.18
    Activations Density 0.041%

    No Known Activations