© 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. 13991
    Prev
    Next
    INDEX
    Explanations

    innate immune system

    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
    åħij
    -0.22
    éľĢè¦ģçĶ¨åĪ°
    -0.20
     chai
    -0.19
    .Invariant
    -0.19
    é«ĺéĵģ
    -0.19
    å¸
    -0.19
     Lux
    -0.19
    vo
    -0.19
    åĨħå¤ĸ
    -0.19
     asleep
    -0.18
    POSITIVE LOGITS
    alone
    0.29
    æ¯Ķè¾ĥç®Ģåįķ
    0.23
    å±ĤéĿ¢
    0.23
    -alone
    0.23
    åħĪè¡Į
    0.22
     Alone
    0.21
    å¾Īç®Ģåįķ
    0.21
    rowse
    0.21
    åıªèĥ½
    0.21
    foundation
    0.20
    Activations Density 0.284%

    No Known Activations