© 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. 21033
    Prev
    Next
    INDEX
    Explanations

    speaking to someone

    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
    ift
    -0.06
     nai
    -0.05
    ival
    -0.05
    ä¸ĭè¾ĸ
    -0.05
    åłĤ
    -0.05
    ifter
    -0.05
    elda
    -0.05
    —
    -0.05
    èªķ
    -0.05
     ÑģÑĭ
    -0.05
    POSITIVE LOGITS
    æ°ĶçļĦ
    0.06
    arah
    0.06
     Ãľn
    0.06
    osci
    0.06
    æģ¯çļĦ
    0.06
    ken
    0.06
    ox
    0.06
    éºŁ
    0.06
    ä½ľåĵģéĽĨ
    0.06
     ponerse
    0.06
    Activations Density 0.010%

    No Known Activations