© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20194
    Prev
    Next
    INDEX
    Explanations

    list definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    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
    æĬķèµĦæĪĸ
    -0.07
     Emple
    -0.06
    个人æĪĸ
    -0.06
    tava
    -0.06
    nyata
    -0.06
    æĢ§æĪĸ
    -0.06
     keine
    -0.06
    æĪĸå¤ļ个
    -0.06
    èĢĥèĻijçļĦ
    -0.06
    åĽ½å®¶æ£®æŀĹåħ¬åĽŃ
    -0.06
    POSITIVE LOGITS
    gin
    0.06
     res
    0.05
    ajn
    0.05
     rense
    0.05
    res
    0.04
    amel
    0.04
     `_
    0.04
    j
    0.04
    çĶĺ
    0.04
    æīĵäºĨ个
    0.04
    Activations Density 0.299%

    No Known Activations