© 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. 32570
    Prev
    Next
    INDEX
    Explanations

    phosphorylation, vector-borne, porous media, coax, light

    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
    使çĶ¨è¯¥
    -0.06
    ail
    -0.06
    å¯¹æľ¬
    -0.06
    ologen
    -0.06
     paternal
    -0.06
    ä»ħæѤ
    -0.06
    å°ĨæīĢæľī
    -0.06
    reeze
    -0.06
     faint
    -0.06
     slightly
    -0.05
    POSITIVE LOGITS
    æĢ§æĪĸ
    0.11
    ãģĦãģŁãĤĬ
    0.09
    æĪĸä¸į
    0.09
    çŃīåħ¶ä»ĸ
    0.09
     hoặc
    0.09
    å·¥ä½ľæĪĸ
    0.08
    æĪĸ
    0.08
    个æĪĸå¤ļ个
    0.08
    ê±°ëĤĺ
    0.08
     Ø£ÙĪ
    0.08
    Activations Density 0.079%

    No Known Activations