© 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. 14727
    Prev
    Next
    INDEX
    Explanations

    point of view

    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
    åŃĹæł·
    -0.22
     PaÅĦst
    -0.20
    onian
    -0.19
    icc
    -0.19
    aption
    -0.19
    åŁĴ
    -0.19
    èħ°
    -0.18
    icens
    -0.18
    åĴ½åĸī
    -0.18
     Bellev
    -0.18
    POSITIVE LOGITS
    è§Ĩè§Ĵ
    0.26
    CSI
    0.23
    缴è¾ĸ
    0.23
    æĹ¥è®°
    0.23
    åıĻè¿°
    0.22
    è®°
    0.21
     perspective
    0.21
     Outs
    0.20
    é£İæł¼
    0.20
    гÑĢан
    0.20
    Activations Density 0.022%

    No Known Activations