© 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. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 89312
    Prev
    Next
    INDEX
    Explanations

    Programming/Technical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ellant
    -0.27
    æĤ¨åIJĮæĦı
    -0.27
    ä¹Łæĺ¯å¦ĤæѤ
    -0.27
    atedRoute
    -0.27
    æĻ°
    -0.26
    anine
    -0.26
    çĽĴåŃIJ
    -0.26
     asn
    -0.25
     fine
    -0.25
     prio
    -0.25
    POSITIVE LOGITS
    éŃģ
    0.27
    æ½®
    0.27
     Ach
    0.26
    沧
    0.26
     participating
    0.26
    åıĤä¸İ
    0.25
    æĺ¨æĹ¥
    0.25
    æľīå¾ħ
    0.25
    uib
    0.25
    çķĮ
    0.25
    Activations Density 13.275%

    No Known Activations