© 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. 15780
    Prev
    Next
    INDEX
    Explanations

    press enter/button, associated documentation

    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
    å¼Ħ
    -0.18
     va
    -0.18
    åħĥ
    -0.18
    ä¸Ģ大
    -0.18
    recursive
    -0.18
    ä¸Ģç¯ĩ
    -0.18
    ãĤ¢ãĥĭ
    -0.18
     CF
    -0.17
    origin
    -0.17
    åīį
    -0.17
    POSITIVE LOGITS
    jang
    0.22
    eper
    0.21
    åħ¶å®ĥéĹ®é¢ĺ
    0.20
    åįģåŃĹ
    0.20
    çŁ³å®¶
    0.19
    åħ³åĪĩ
    0.19
    _br
    0.19
    骸
    0.18
    sse
    0.18
    濯
    0.18
    Activations Density 0.003%

    No Known Activations