© 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. 39789
    Prev
    Next
    INDEX
    Explanations

    circular, binomial, zero, Dolph, suggested, haven't, melanoma, scorpion

    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
    klet
    -0.09
    _HELPER
    -0.08
    ONG
    -0.08
    itudine
    -0.08
    å·¡è§Ĩåijĺ
    -0.08
    管å±Ģ
    -0.08
    ILED
    -0.08
    yg
    -0.08
    ä¸ĩä¸Ī
    -0.08
    ondon
    -0.07
    POSITIVE LOGITS
    çĶ¨äºİ
    0.08
     weights
    0.07
    åĩij
    0.07
    ä¸Ģç»Ħ
    0.07
    é«ĺæķĪ
    0.07
     Cherry
    0.07
     weighting
    0.06
     Pain
    0.06
    移æ¤į
    0.06
    weights
    0.06
    Activations Density 0.005%

    No Known Activations