© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2041
    Prev
    Next
    INDEX
    Explanations

    statistical comparison and analysis

    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
     cÆ°
    -0.07
    ymph
    -0.07
    çĮ¿
    -0.07
    åij¤
    -0.07
     incident
    -0.07
    incid
    -0.07
    æķ·
    -0.07
    itsu
    -0.06
     Incident
    -0.06
    oque
    -0.06
    POSITIVE LOGITS
     pairwise
    0.10
     grouping
    0.07
     ordinal
    0.07
    (groups
    0.07
    对åIJĦ
    0.07
     Ordering
    0.07
    æŨ
    0.07
     judgement
    0.07
     GLES
    0.07
    åĪĨç»Ħ
    0.07
    Activations Density 0.003%

    No Known Activations