© 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. 89206
    Prev
    Next
    INDEX
    Explanations

    Foundation

    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
    ä¸įåĥı
    -0.29
     cheaper
    -0.26
    drs
    -0.25
    æĽ¿æį¢
    -0.25
    å®ļçĤ¹
    -0.25
    olls
    -0.24
     distributor
    -0.24
    flate
    -0.24
    举åĬ¨
    -0.23
     devastation
    -0.23
    POSITIVE LOGITS
    ald
    0.27
     boa
    0.27
    yard
    0.26
    çijľä¼½
    0.25
     hòa
    0.24
    cont
    0.24
    ÅĻ
    0.23
    .eye
    0.23
    ROUP
    0.23
     risk
    0.23
    Activations Density 7.991%

    No Known Activations