© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 29913
    Prev
    Next
    INDEX
    Explanations

    credit score and risk

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç¾½
    -0.08
    éľĵ
    -0.08
    å¥ĩå¦ĻçļĦ
    -0.07
    онаÑĤ
    -0.07
    èĤ¡æ°ij
    -0.07
    åĩıç¨İ
    -0.07
    cev
    -0.07
    OUCH
    -0.07
    ialized
    -0.07
    çon
    -0.06
    POSITIVE LOGITS
     risk
    0.10
    è¯Ħ级
    0.10
     borrower
    0.09
    é£İéĻ©
    0.09
    é£İéĻ©è¯Ħä¼°
    0.09
    Risk
    0.09
     Risk
    0.09
    -risk
    0.09
    ä¿¡çĶ¨
    0.09
     borrowers
    0.08
    Activations Density 0.035%

    No Known Activations