© 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. 8183
    Prev
    Next
    INDEX
    Explanations

    academic texts

    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
    -plus
    -0.32
     Bern
    -0.28
    ince
    -0.28
    åĩı
    -0.28
     plus
    -0.28
     embodiment
    -0.27
    plus
    -0.27
    rip
    -0.27
     Plus
    -0.27
    Plus
    -0.27
    POSITIVE LOGITS
    rame
    0.29
    åįģä¸ĩ
    0.27
    Git
    0.24
     Swap
    0.24
    etry
    0.24
     aure
    0.24
    è¶Ĭä¾Ĩè¶Ĭ
    0.24
    追ãģĦ
    0.24
    .nano
    0.23
    å¸Ĥåľºè§Ħ模
    0.23
    Activations Density 0.019%

    No Known Activations