© 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. 89803
    Prev
    Next
    INDEX
    Explanations

    technical/coding language

    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
     Sparks
    -0.27
    edly
    -0.26
    enie
    -0.25
    æĹ¶è¡¨ç¤º
    -0.25
    PX
    -0.25
    licensed
    -0.24
    cket
    -0.24
    åIJįçīĮ
    -0.24
    oulos
    -0.23
    aptors
    -0.23
    POSITIVE LOGITS
    èIJ½åľ¨
    0.27
     messing
    0.25
    Obs
    0.25
    sse
    0.24
     //↵
    0.24
    },{"
    0.24
    伫
    0.24
    çĥĽ
    0.24
    otte
    0.23
    //(
    0.23
    Activations Density 21.015%

    No Known Activations