© 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. 39708
    Prev
    Next
    INDEX
    Explanations

    multi-level, multi-loop, composition, SignTx, minor

    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
    igi
    -0.07
    èĹķ
    -0.06
    èī¯æĢ§
    -0.06
    åīįéĢĶ
    -0.06
    -keys
    -0.06
    å§
    -0.06
    èĦī
    -0.06
    èĴ
    -0.06
    pul
    -0.05
     aqu
    -0.05
    POSITIVE LOGITS
    odyn
    0.08
    attore
    0.08
     dolore
    0.08
    abox
    0.08
    Skeleton
    0.08
    Ĩµ
    0.08
    åķĨäºĭ
    0.08
    htdocs
    0.08
    lighet
    0.07
    åĴĮè§ĦèĮĥ
    0.07
    Activations Density 0.005%

    No Known Activations