© 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. 12441
    Prev
    Next
    INDEX
    Explanations

    cubed, diced, pieces, finely, powdered

    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
    è¦ģç´ł
    -0.23
    æ°¸ä¹ħ
    -0.20
    alone
    -0.20
    ç®Ģ约
    -0.19
    è¾Ī
    -0.19
     SIMPLE
    -0.19
    esta
    -0.18
    eye
    -0.18
    综åIJĪæĢ§
    -0.18
    ifa
    -0.18
    POSITIVE LOGITS
    chunk
    0.21
    åĿĹ
    0.20
    大大å°ı
    0.20
    setSize
    0.19
    èĮ§
    0.19
     redemption
    0.18
    声åĵį
    0.18
    оÑĢм
    0.18
    éĺ±
    0.18
    rapid
    0.18
    Activations Density 0.004%

    No Known Activations