© 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. 20-TRANSCODER-HP
    7. 140963
    Prev
    Next
    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /blue
    -0.28
    æĶ¶å®ĺ
    -0.27
    èµŃ
    -0.26
    é²ľ
    -0.26
    BC
    -0.24
     Legislation
    -0.24
    @@
    -0.24
     repl
    -0.23
    IC
    -0.23
    ä¹łæĥ¯äºĨ
    -0.23
    POSITIVE LOGITS
    anmar
    0.29
    illy
    0.28
    trak
    0.26
    è¿Ļæīįæĺ¯
    0.26
    niej
    0.26
    -tm
    0.26
    iley
    0.25
    ertext
    0.25
    idable
    0.25
    oload
    0.25
    Activations Density 41.015%

    No Known Activations