© 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. 30796
    Prev
    Next
    INDEX
    Explanations

    activities

    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
     à¤ķाà¤Ĥà¤Ĺ
    -0.09
    IfNeeded
    -0.08
    ValuePair
    -0.08
    ÎŃÏģγ
    -0.08
    },{"
    -0.08
    åľ°ä¹ħ
    -0.08
    áĥ§áĥĿ
    -0.08
    esai
    -0.08
    ève
    -0.08
    /*/
    -0.08
    POSITIVE LOGITS
    0.07
    _
    0.07
    -
    0.06
    b
    0.06
    d
    0.06
    “
    0.06
    one
    0.06
    1
    0.06
    urant
    0.06
    åıijçĶŁäºĨä»Ģä¹Ī
    0.05
    Activations Density 0.754%

    No Known Activations