© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20968
    Prev
    Next
    INDEX
    Explanations

    keep in mind

    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
    tf
    -0.06
    ter
    -0.06
    ten
    -0.06
    adel
    -0.05
    ãĤ±
    -0.05
    teh
    -0.05
    ts
    -0.05
    ces
    -0.05
    çħŀ
    -0.05
     Aren
    -0.05
    POSITIVE LOGITS
    nowled
    0.08
    çĿĢä¸Ģé¢Ĺ
    0.06
    inig
    0.06
    å·²ä¹ħçļĦ
    0.06
    fortun
    0.06
    æłijä¸Ģ
    0.06
    ceptor
    0.06
    abinet
    0.06
    äºĨä¸Ģå®ļçļĦ
    0.06
    iog
    0.06
    Activations Density 0.004%

    No Known Activations