© 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. 10871
    Prev
    Next
    INDEX
    Explanations

    hazardous flammable energetic explosive

    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
    å§ĭçļĩ
    -0.08
    çī¹åĭĴ
    -0.08
     imposta
    -0.08
    ä¸ĭå²Ĺ
    -0.08
    èĥĥçĹħ
    -0.08
    ivio
    -0.08
    ionar
    -0.07
    èĥĥçĹĽ
    -0.07
    itter
    -0.07
    åħ´åĽ½
    -0.07
    POSITIVE LOGITS
     ignite
    0.10
    åı¯çĩĥ
    0.10
    æĺĵçĩĥ
    0.09
    å¼ķçĪĨ
    0.09
     deton
    0.09
     explos
    0.09
     ignition
    0.09
    åį±éĻ©æĢ§
    0.09
     explosive
    0.08
    èĦĨå¼±
    0.08
    Activations Density 0.009%

    No Known Activations