© 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. 14412
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    lasse
    -0.09
    ignano
    -0.09
    naver
    -0.09
    berechtig
    -0.09
    igni
    -0.08
    kong
    -0.08
    ChangeEvent
    -0.08
    resta
    -0.08
    eldo
    -0.08
    piegel
    -0.08
    POSITIVE LOGITS
    ach
    0.07
    w
    0.07
    wok
    0.06
    _sensitive
    0.06
    abl
    0.06
    éļıå¤Ħåı¯è§ģ
    0.06
     accr
    0.05
    åľ°çĭ±
    0.05
    æĭīä½ı
    0.05
     rais
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.