© 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. 89470
    Prev
    Next
    INDEX
    Explanations

    creation/design

    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
    cá
    -0.28
    å§Ķå±Ī
    -0.27
     enclosed
    -0.26
    åĩºçİ°äºĨ
    -0.26
     Yaz
    -0.26
     bó
    -0.26
    .”↵↵↵↵
    -0.25
    å°ģ
    -0.25
    ounces
    -0.25
    ched
    -0.25
    POSITIVE LOGITS
     norm
    0.34
    norm
    0.31
     Norm
    0.27
    iere
    0.26
     detachment
    0.26
    ä¸Ģè´¯
    0.26
     fore
    0.25
    件
    0.25
     res
    0.24
    ips
    0.24
    Activations Density 3.372%

    No Known Activations