© 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. 27-TRANSCODER-HP
    7. 8481
    Prev
    Next
    INDEX
    Explanations

    Unstructured/semi-structured data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĩ®
    -0.26
    ::<
    -0.25
    _tac
    -0.25
    éĺ¶
    -0.23
    ignment
    -0.23
    idis
    -0.23
     grief
    -0.23
    orient
    -0.23
    æĴŃ
    -0.23
     convenience
    -0.23
    POSITIVE LOGITS
    omba
    0.27
    datum
    0.26
    енÑĤа
    0.25
    TED
    0.25
     Dollar
    0.25
    IRD
    0.24
    uccess
    0.24
    ä¼ļéķ¿
    0.24
     metre
    0.24
     cms
    0.23
    Activations Density 0.002%

    No Known Activations