© 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. 9283
    Prev
    Next
    INDEX
    Explanations

    punctuation, mostly commas

    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
    tas
    -0.31
    igator
    -0.26
    ta
    -0.26
    prove
    -0.26
    å°ĺ
    -0.25
    çijľ
    -0.25
    aneous
    -0.25
    .dsl
    -0.24
    prov
    -0.24
    åŃĺåľ¨
    -0.24
    POSITIVE LOGITS
    çķĮ
    0.29
    omon
    0.28
    å¾Īåı¯èĥ½
    0.27
    åįķä»·
    0.27
     recipro
    0.26
     Tib
    0.25
    麼
    0.24
    å¿ħçĦ¶
    0.24
    çķĮçļĦ
    0.24
    (axis
    0.24
    Activations Density 0.066%

    No Known Activations