© 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. 33-TRANSCODER-HP
    7. 54031
    Prev
    Next
    INDEX
    Explanations

    Completes "ance/ence" suffix

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åıĮçľ¼
    -0.27
    DIFF
    -0.27
    vf
    -0.27
    åŃ©
    -0.25
    -fetch
    -0.25
     litigation
    -0.24
    ini
    -0.24
    /Graphics
    -0.24
    /cc
    -0.24
     bargaining
    -0.24
    POSITIVE LOGITS
    styleType
    0.29
    åºĬä¸Ĭ
    0.27
    ieber
    0.27
    align
    0.25
    ehler
    0.24
    书åĨĻ
    0.24
    ashi
    0.24
    ward
    0.24
    å
    0.24
    ///č↵
    0.24
    Activations Density 0.007%

    No Known Activations