© 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. 8825
    Prev
    Next
    INDEX
    Explanations

    online activities/business

    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
    thin
    -0.26
     ],č↵
    -0.25
    CTL
    -0.25
     /*č↵
    -0.25
    },č↵
    -0.25
    CTX
    -0.25
    ndef
    -0.24
     .č↵
    -0.24
     quotient
    -0.24
     DefaultValue
    -0.24
    POSITIVE LOGITS
     pal
    0.27
    ä¾Ŀæį®
    0.26
    ops
    0.25
    éĶĻ
    0.25
    err
    0.25
    cedure
    0.24
     {_
    0.24
    éĺIJæĺİ
    0.24
    åº
    0.24
    ä¸įåºĶ该
    0.23
    Activations Density 0.005%

    No Known Activations