© 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. 19107
    Prev
    Next
    INDEX
    Explanations

    code library functions

    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
    надÑĨ
    -0.06
     scarc
    -0.06
    elh
    -0.06
    ailles
    -0.06
    hs
    -0.06
    μι
    -0.05
    imet
    -0.05
     chaî
    -0.05
    amel
    -0.05
    alternate
    -0.05
    POSITIVE LOGITS
     pass
    0.06
     won
    0.05
    ahari
    0.05
    avn
    0.05
    IPS
    0.05
    arming
    0.05
    ovar
    0.05
    åľ¨è¿Ļ
    0.05
    æĺ¯ä¸¤ä¸ª
    0.05
     ferm
    0.05
    Activations Density 0.008%

    No Known Activations