© 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. 20531
    Prev
    Next
    INDEX
    Explanations

    section headers

    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
     subsequently
    -0.06
    eres
    -0.05
    /documentation
    -0.05
    /wp
    -0.05
    寸
    -0.05
    å°¤åħ¶åľ¨
    -0.05
    åľ¨æľ¬
    -0.05
    对该
    -0.05
     accounting
    -0.05
     playing
    -0.05
    POSITIVE LOGITS
     WTF
    0.06
     recogida
    0.06
    éĽªçĻ½çļĦ
    0.06
     aven
    0.06
    åħ¨åĬĽæīĵéĢł
    0.06
    çļĦäºĨ
    0.06
    NháºŃn
    0.06
    sn
    0.06
    åĬªåĬĽæīĵéĢł
    0.06
    nce
    0.06
    Activations Density 0.490%

    No Known Activations