© 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. 30-TRANSCODER-HP
    7. 95615
    Prev
    Next
    INDEX
    Explanations

    letters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æķ°çłģ
    -0.34
    éĺ¿æĭī伯
    -0.28
     ÑĨиÑĦ
    -0.27
    acin
    -0.27
     Caller
    -0.27
     dig
    -0.26
     DIG
    -0.26
    RIA
    -0.26
     arab
    -0.26
    indi
    -0.26
    POSITIVE LOGITS
     fourteen
    0.37
     letters
    0.36
    åįģä¸Ģ
    0.36
    åįģåħŃ
    0.36
    åįģäºĶ
    0.35
    åįģåĽĽ
    0.35
     twelve
    0.35
     eleven
    0.35
     letter
    0.35
    _letter
    0.34
    Activations Density 0.924%

    No Known Activations