© 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. 18-TRANSCODER-HP
    7. 89474
    Prev
    Next
    INDEX
    Explanations

    resources and materials

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xFFFFFFFF
    -0.29
    ubre
    -0.29
    NumberFormatException
    -0.26
    å¾Īé«ĺ
    -0.26
    )<<
    -0.26
    stantiate
    -0.25
    IPS
    -0.25
    åį´
    -0.24
    subtype
    -0.23
    oxic
    -0.23
    POSITIVE LOGITS
    uco
    0.26
    ä¼łç»ŁçļĦ
    0.25
    -panel
    0.25
    ->↵
    0.25
    +',
    0.25
    交
    0.24
    èģĶåIJĪä¼ļ
    0.24
     panels
    0.23
    bond
    0.23
    -Jul
    0.23
    Activations Density 13.289%

    No Known Activations