© 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. 20627
    Prev
    Next
    INDEX
    Explanations

    loan or mortgage

    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
    uhu
    -0.08
    èµ°å¼±
    -0.07
    tvr
    -0.07
    wegs
    -0.07
    游走
    -0.06
     fantasi
    -0.06
    ufr
    -0.06
    utri
    -0.06
     korona
    -0.06
    该软件
    -0.06
    POSITIVE LOGITS
    0.06
     V
    0.06
    亦
    0.05
    V
    0.05
    å®ľ
    0.05
    ated
    0.05
     again
    0.05
    ells
    0.05
    åĨį次
    0.05
     bil
    0.04
    Activations Density 0.005%

    No Known Activations