© 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. 13965
    Prev
    Next
    INDEX
    Explanations

    carcinogenesis

    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
     discharge
    -0.08
     discharged
    -0.07
    artic
    -0.07
    æĸ¤
    -0.07
    cake
    -0.06
    ç»ıæµİåľĪ
    -0.06
    çĶĺéľ²
    -0.06
     Lip
    -0.06
    å®ŀéĻħéľĢè¦ģ
    -0.06
    che
    -0.06
    POSITIVE LOGITS
    èĩ´çĻĮ
    0.17
     carcin
    0.15
     cancer
    0.12
     cancers
    0.11
    çĻĮ
    0.10
     Cancer
    0.10
    çĻĮçĹĩ
    0.10
     سرطاÙĨ
    0.09
    æĬĹçĻĮ
    0.09
    é£İéĻ©è¯Ħä¼°
    0.09
    Activations Density 0.235%

    No Known Activations