© 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. 96327
    Prev
    Next
    INDEX
    Explanations

    Scientific/technical terminology

    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
    nant
    -0.29
    Fan
    -0.28
     sb
    -0.27
    缮
    -0.26
    rics
    -0.25
    Mappings
    -0.25
    sb
    -0.25
    为大家
    -0.24
     ham
    -0.24
    SB
    -0.24
    POSITIVE LOGITS
     bure
    0.25
    /mac
    0.25
    (deg
    0.25
    BOSE
    0.24
    agos
    0.24
    ighet
    0.24
    eling
    0.23
    ез
    0.23
    ailing
    0.23
     deps
    0.23
    Activations Density 0.002%

    No Known Activations