© 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. 17393
    Prev
    Next
    INDEX
    Explanations

    function arguments

    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
    egin
    -0.06
    z
    -0.05
    åĶ®
    -0.05
    å±ħ
    -0.05
    re
    -0.05
    åIJ§
    -0.05
    å±±æ¹ĸ
    -0.05
    к
    -0.05
    rina
    -0.05
    å¸ĥ
    -0.05
    POSITIVE LOGITS
    auf
    0.08
    weise
    0.07
    bahan
    0.07
    çĬ¹æľªå°½
    0.06
    digt
    0.06
    omens
    0.06
    понен
    0.06
     outs
    0.06
    çħĮ
    0.06
     ilan
    0.06
    Activations Density 0.052%

    No Known Activations