© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7066
    Prev
    Next
    INDEX
    Explanations

    order

    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
    ####↵
    -0.34
    -scrollbar
    -0.27
    reature
    -0.26
    .timestamps
    -0.26
    setattr
    -0.26
    caps
    -0.25
     //</
    -0.25
    æĻ®æĥł
    -0.24
    doors
    -0.24
    bove
    -0.24
    POSITIVE LOGITS
    ç¼ĺ
    0.33
    edly
    0.28
     hypoth
    0.27
    次æķ°
    0.27
     hyp
    0.26
    ÑĤип
    0.26
    éĺ³åİ¿
    0.26
    头
    0.26
     mill
    0.26
    åĴ³
    0.26
    Activations Density 1.868%

    No Known Activations