© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18910
    Prev
    Next
    INDEX
    Explanations

    universal values

    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
    ase
    -0.06
    arse
    -0.06
    oto
    -0.06
    èĭĽ
    -0.05
    ol
    -0.05
    lot
    -0.05
    ati
    -0.05
    ose
    -0.05
    ote
    -0.05
    lots
    -0.05
    POSITIVE LOGITS
    lande
    0.06
    ehrte
    0.06
    DEFINED
    0.06
    亲
    0.05
    人大
    0.05
    emies
    0.05
    éĻ¢
    0.05
    å¦ĥ
    0.05
    hadap
    0.05
     recons
    0.05
    Activations Density 0.012%

    No Known Activations