© 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. 61701
    Prev
    Next
    INDEX
    Explanations

    long-term relationship

    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
    -0.08
    ...
    -0.06
    od
    -0.06
    éĢ
    -0.06
    es
    -0.06
    <|fim_suffix|>
    -0.05
    âĢ¦
    -0.05
     --
    -0.05
    -0.05
    ay
    -0.05
    POSITIVE LOGITS
    èĬ·
    0.09
    _OCCURRED
    0.09
    ãĤ¹ãĤ¹ãĥ¡
    0.09
    ggia
    0.09
    ñas
    0.09
    corre
    0.09
    {}",
    0.09
    rotch
    0.08
    **–
    0.08
    ingkatkan
    0.08
    Activations Density 0.005%

    No Known Activations