© 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. 30-TRANSCODER-HP
    7. 95336
    Prev
    Next
    INDEX
    Explanations

    eye anatomy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ariat
    -0.28
    åıįå¼¹
    -0.26
    楼主
    -0.24
    åĤ¬åĮĸ
    -0.24
    âĺİ
    -0.24
    åIJ¬è¯Ŀ
    -0.23
    线ä¸Ĭ线ä¸ĭ
    -0.23
    -lines
    -0.23
    kers
    -0.23
    ç¬Ļ
    -0.23
    POSITIVE LOGITS
     DOC
    0.29
    ap
    0.28
    æĥķ
    0.26
     Tart
    0.26
    æŃ
    0.25
    éĥ¨
    0.25
    tex
    0.25
     dominated
    0.24
    è¯Ń
    0.24
    æ¹Ľ
    0.24
    Activations Density 0.789%

    No Known Activations