© 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. 50510
    Prev
    Next
    INDEX
    Explanations

    self, internal, themselves

    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
    çĻ¾æĪĺ
    -0.08
    yder
    -0.07
    ALER
    -0.07
    ä¸Ĭè¿°äºĭå®ŀ
    -0.07
    çĶŁç´ł
    -0.07
    _planes
    -0.07
    ucc
    -0.07
    ÑĢид
    -0.07
    -strip
    -0.06
    å¹³çĶŁ
    -0.06
    POSITIVE LOGITS
     self
    0.18
     internal
    0.18
     Self
    0.18
    _self
    0.18
    åĨħéĥ¨
    0.17
    -self
    0.17
     internally
    0.17
     SELF
    0.16
    Self
    0.16
    èĩªæĪij
    0.16
    Activations Density 0.489%

    No Known Activations