© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6089
    Prev
    Next
    INDEX
    Explanations

    Numbers and lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IPS
    -0.28
    ledo
    -0.26
    uese
    -0.25
    ipse
    -0.25
    HM
    -0.25
    igure
    -0.25
    gne
    -0.24
    转移
    -0.23
    (SP
    -0.23
     keeping
    -0.22
    POSITIVE LOGITS
    çļĦ帮åĬ©
    0.24
    天èĬ±æĿ¿
    0.24
    des
    0.24
    DataURL
    0.23
     Nass
    0.23
    èĢĹ
    0.23
    eneg
    0.23
    stück
    0.23
     Drew
    0.23
     Constit
    0.23
    Activations Density 0.043%

    No Known Activations