© 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. 18065
    Prev
    Next
    INDEX
    Explanations

    feel like

    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
    ly
    -0.07
     dÃłng
    -0.06
    ing
    -0.06
    -enable
    -0.06
    emente
    -0.06
    illet
    -0.06
    ally
    -0.05
    åħĪçĶŁçļĦ
    -0.05
    indo
    -0.05
    åħĪçĶŁåľ¨
    -0.05
    POSITIVE LOGITS
    sa
    0.07
    дÑĭ
    0.06
    Ø´
    0.06
    çĤ¹èĩ³
    0.06
    siniz
    0.06
    atif
    0.06
    wad
    0.06
    avier
    0.06
    ivity
    0.06
    _repr
    0.06
    Activations Density 0.005%

    No Known Activations