© 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. 56909
    Prev
    Next
    INDEX
    Explanations

    binary

    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
    rient
    -0.26
    éĺĶ
    -0.25
     wrongly
    -0.25
    /MIT
    -0.25
    èıĮ
    -0.24
    elson
    -0.24
    thon
    -0.24
    ائÙĬÙĦ
    -0.24
    @protocol
    -0.24
    oles
    -0.24
    POSITIVE LOGITS
    -safe
    0.27
     thirds
    0.27
    ocular
    0.27
    ublished
    0.27
    na
    0.27
    nd
    0.26
    ä¸įæĺ¯ä¸Ģ个
    0.24
    emed
    0.24
     adipiscing
    0.23
    ä¸ĭåij¨
    0.23
    Activations Density 0.014%

    No Known Activations