© 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. 19-TRANSCODER-HP
    7. 8312
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itemprop
    -0.26
    åŃ£åIJİ
    -0.26
     rails
    -0.26
    __,__
    -0.25
    itol
    -0.25
    çĦ¶æĺ¯
    -0.25
     retiring
    -0.25
    åĶ±
    -0.24
    åĭŀ
    -0.24
    wargs
    -0.24
    POSITIVE LOGITS
    omat
    0.27
    å®ļæŶ
    0.27
    ãĤ«
    0.27
    åħ·ä½ĵ
    0.26
    iga
    0.26
    æĬij
    0.25
    çķª
    0.24
    uner
    0.24
    idon
    0.24
    éĥģ
    0.24
    Activations Density 0.001%

    No Known Activations