© 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. 88904
    Prev
    Next
    INDEX
    Explanations

    Expressing sentiments/opinions

    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
    ogr
    -0.28
    åħ¼
    -0.25
     transition
    -0.25
     AND
    -0.25
    çĴĭ
    -0.24
    éĨ®
    -0.24
    注
    -0.24
     vie
    -0.24
    WithOptions
    -0.24
    isque
    -0.23
    POSITIVE LOGITS
    é¾Ļ头
    0.28
     Sanct
    0.26
    ä»ĸ们æĺ¯
    0.25
    第ä¸Ģ书记
    0.25
    -expanded
    0.24
    leston
    0.24
    _numer
    0.24
    calc
    0.23
    enuine
    0.23
     Vac
    0.23
    Activations Density 22.490%

    No Known Activations