© 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. 30693
    Prev
    Next
    INDEX
    Explanations

    basis

    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
    apati
    -0.07
    å°±ä¸įçĶ¨
    -0.07
    çĭ¬åĪ°
    -0.07
    éģ¿
    -0.07
    åĽłä¸ºæľī
    -0.07
    bjerg
    -0.07
    åħįå¾Ĺ
    -0.07
    stor
    -0.07
    stadt
    -0.06
    äºĪ
    -0.06
    POSITIVE LOGITS
    åħ¨éĿł
    0.09
    ä¾ĿéĿł
    0.09
    ä¹Łåıªèĥ½
    0.09
    åıªèĥ½éĢļè¿ĩ
    0.08
    æĪijåıªèĥ½
    0.08
    åıªèĥ½
    0.08
    è¦ģéĿł
    0.08
    ãģĹãģĭ
    0.08
    —which
    0.07
    å°±åıªèĥ½
    0.07
    Activations Density 0.135%

    No Known Activations