© 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. 20440
    Prev
    Next
    INDEX
    Explanations

    stanozolol, demeter, ages, rds pricing, badescu

    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
    éªĭ
    -0.08
    .Acc
    -0.07
    plode
    -0.07
    .FIELD
    -0.06
    èľ¿
    -0.06
    //@
    -0.06
    _TOGGLE
    -0.06
    cik
    -0.06
    edi
    -0.06
    çĦ¶å¤§
    -0.06
    POSITIVE LOGITS
    itut
    0.08
    leit
    0.08
    _vs
    0.07
    çĻ¾åº¦çĻ¾ç§ij
    0.07
    ÑĪÑĤо
    0.07
    ä¸įä»ħåľ¨
    0.07
    åĩłä¹İ
    0.07
    主è¦ģåĪĨ为
    0.07
    iton
    0.07
    /images
    0.07
    Activations Density 0.002%

    No Known Activations