© 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. 21676
    Prev
    Next
    INDEX
    Explanations

    Âł separator

    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
    thinkable
    -0.07
    forgettable
    -0.06
    paralleled
    -0.06
    ette
    -0.06
    iente
    -0.06
    iture
    -0.06
    anz
    -0.06
    nungs
    -0.05
    ä¸įçĦ¶
    -0.05
    ound
    -0.05
    POSITIVE LOGITS
    s
    0.09
    aros
    0.07
    tok
    0.07
    ä»ħæıIJä¾Ľ
    0.07
    ï¸ı
    0.07
    lect
    0.06
    ÑĢÑıдÑĥ
    0.06
    self
    0.06
    acer
    0.06
    ti
    0.06
    Activations Density 0.036%

    No Known Activations