© 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. 17508
    Prev
    Next
    INDEX
    Explanations

    interpolation between points

    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
    ph
    -0.06
    æ½Ķ
    -0.06
     scale
    -0.06
    udit
    -0.06
    cope
    -0.06
    asl
    -0.06
    æ´ģ
    -0.06
    æ£Ģåĩº
    -0.06
    åĩĢ
    -0.05
     scales
    -0.05
    POSITIVE LOGITS
     interpolation
    0.09
     interpolated
    0.08
     interpol
    0.08
     interpolate
    0.07
    .interpolate
    0.07
    æıĴ
    0.07
    polation
    0.06
    对æĪĺ
    0.06
    ме
    0.06
     Antoni
    0.06
    Activations Density 0.020%

    No Known Activations