© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 9233
    Prev
    Next
    INDEX
    Explanations

    als neuron

    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
    åħ¶æŀĹ
    -0.07
    èĮľ
    -0.07
    ç¬Ķä¸ĭ
    -0.06
    åĩ
    -0.06
    ulia
    -0.06
     Sims
    -0.06
    émission
    -0.06
    ikov
    -0.06
    èĥ½ä¸º
    -0.06
    ç¬Ķä¸ĭçļĦ
    -0.06
    POSITIVE LOGITS
     ident
    0.08
    å¿ĺè®°
    0.08
    alley
    0.08
    phia
    0.07
    éĺ¶
    0.07
    laÅŁ
    0.07
    -muted
    0.07
    ä¸įç»ı
    0.07
    ıp
    0.07
    åĨįä¸Ģ次
    0.07
    Activations Density 0.289%

    No Known Activations