© 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. 7338
    Prev
    Next
    INDEX
    Explanations

    End of sentence or phrase

    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
    çĥĺ
    -0.33
    contr
    -0.30
    structions
    -0.28
    iously
    -0.27
     contr
    -0.27
    å±ıèĶ½
    -0.27
    å·¦åı³
    -0.26
    inge
    -0.26
    æĸĩåĮĸ
    -0.25
    æļĦ
    -0.25
    POSITIVE LOGITS
     sez
    0.29
     Ending
    0.26
    icable
    0.25
    anse
    0.24
    ä¹Ĵä¹ĵ
    0.24
    à®ĥ
    0.24
    ||(
    0.24
     Investor
    0.23
    ousy
    0.23
    еÑĩа
    0.23
    Activations Density 0.023%

    No Known Activations