© 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. 11995
    Prev
    Next
    INDEX
    Explanations

    required size or quantity

    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
    PropertyValue
    -0.21
    天é¹ħ
    -0.20
    locker
    -0.20
    éĹ®åĢĻ
    -0.20
    æľī趣çļĦ
    -0.19
    ôi
    -0.19
    æĨ¬
    -0.19
    AGON
    -0.19
    éĹ®è¯¢
    -0.19
    iterated
    -0.19
    POSITIVE LOGITS
     needed
    0.32
    æīįèĥ½
    0.29
     required
    0.29
     accordingly
    0.29
    åIJĪéĢĤ
    0.27
    Needed
    0.27
    _needed
    0.26
    è¦ģæľī
    0.26
    è¶³å¤ŁçļĦ
    0.26
     нÑĥжнÑĭ
    0.26
    Activations Density 0.202%

    No Known Activations