© 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. 96555
    Prev
    Next
    INDEX
    Explanations

    Scientific/mathematical abstracts

    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
     theory
    -0.31
    çIJĨ论
    -0.29
    etta
    -0.29
    èĢ³
    -0.29
    theory
    -0.29
    åł¡
    -0.28
    etail
    -0.27
     suff
    -0.26
    -model
    -0.25
    edList
    -0.25
    POSITIVE LOGITS
    gage
    0.28
     поб
    0.26
    pite
    0.25
    -packages
    0.24
    ploy
    0.24
    VN
    0.24
     Gel
    0.24
    æķ£
    0.24
     Barg
    0.24
     geh
    0.24
    Activations Density 0.898%

    No Known Activations