© 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. 13584
    Prev
    Next
    INDEX
    Explanations

    research servers, track, boat

    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
     íķŃ
    -0.20
    æļ§
    -0.19
     SAY
    -0.19
    horn
    -0.18
    edy
    -0.18
    lain
    -0.18
    SOR
    -0.18
     promot
    -0.18
     Bakan
    -0.18
     handc
    -0.17
    POSITIVE LOGITS
    èĤ©
    0.25
    泡
    0.20
    æīİ
    0.20
    èĦį
    0.19
    ughs
    0.19
    å¯Ħ
    0.19
    å®Ŀè´µ
    0.19
    çİ°éĺ¶æ®µ
    0.19
     cascade
    0.18
    èĢģ人家
    0.18
    Activations Density 0.437%

    No Known Activations