© 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. 88782
    Prev
    Next
    INDEX
    Explanations

    code

    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
    åĴĮæľįåĬ¡
    -0.29
    ulings
    -0.28
    æĥ³å¿µ
    -0.27
     offsetof
    -0.25
     illegally
    -0.25
     Tuesday
    -0.24
     Telegraph
    -0.24
    ç»ıå¼Ģ
    -0.24
    reau
    -0.24
    ardy
    -0.24
    POSITIVE LOGITS
    heel
    0.27
    civil
    0.26
    roma
    0.25
    yle
    0.25
    rist
    0.25
    马æĭī
    0.25
    roup
    0.25
    å°±åľ¨
    0.24
    ******↵
    0.24
     self
    0.24
    Activations Density 1.530%

    No Known Activations