© 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. 62972
    Prev
    Next
    INDEX
    Explanations

    not followed by word

    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
     não
    -0.09
    ä¸įæĩĪåĬªåĬĽ
    -0.09
    voud
    -0.08
     nutshell
    -0.08
    stral
    -0.08
    iczny
    -0.08
    ÙĬÙĪر
    -0.08
    manuel
    -0.08
    cope
    -0.08
    nable
    -0.07
    POSITIVE LOGITS
    tingham
    0.15
    ional
    0.13
    oriously
    0.13
     obstante
    0.12
    withstanding
    0.12
    epad
    0.11
    ches
    0.11
     yet
    0.11
     necessarily
    0.11
    ching
    0.10
    Activations Density 0.196%

    No Known Activations