© 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. 89449
    Prev
    Next
    INDEX
    Explanations

    Technical documents

    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
    amt
    -0.28
    æŁ³
    -0.28
    als
    -0.27
    åħ¼åħ·
    -0.26
    河西
    -0.26
    çݰ代
    -0.25
    åŁºäºİ
    -0.25
     AST
    -0.25
     IW
    -0.25
     accommod
    -0.24
    POSITIVE LOGITS
    .Mask
    0.28
     Guerr
    0.28
    bare
    0.27
    wen
    0.27
    çľ¼çļ®
    0.26
    ieve
    0.26
     ltd
    0.26
    @\
    0.25
    èħĭ
    0.24
    åİ¿æĶ¿åºľ
    0.24
    Activations Density 17.738%

    No Known Activations