© 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. 16560
    Prev
    Next
    INDEX
    Explanations

    climbing climbers

    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
    秧
    -0.21
    usher
    -0.21
    çĺŁ
    -0.20
    讽
    -0.20
    滥
    -0.20
    亩
    -0.19
    æģ«
    -0.19
    æī¹
    -0.19
     Vil
    -0.19
     Pri
    -0.19
    POSITIVE LOGITS
    æĶĢçĻ»
    0.30
    æĶĢ
    0.29
    çĪ¬
    0.25
    çĻ»å±±
    0.24
    磴
    0.24
    æĬĢå·§
    0.23
    èĥĮåĮħ
    0.23
    æīĢéľĢçļĦ
    0.23
    åı°éĺ¶
    0.23
    éľĢè¦ģçĶ¨åĪ°
    0.23
    Activations Density 0.016%

    No Known Activations