© 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. 27-TRANSCODER-HP
    7. 57756
    Prev
    Next
    INDEX
    Explanations

    Finland

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ELS
    -0.28
     dilation
    -0.23
    å£ħ
    -0.23
    éĻIJæŶ
    -0.23
    ìķ¼
    -0.23
     Catalan
    -0.23
     Defaults
    -0.23
    便ç§ĺ
    -0.23
    æŀī
    -0.23
     china
    -0.22
    POSITIVE LOGITS
    ers
    0.29
    er
    0.28
    typ
    0.26
    erb
    0.24
    è¿ĩ
    0.24
    /***************************************************************************↵
    0.23
    ä¼´
    0.23
    omic
    0.23
    ãĥ¼ãĤ·
    0.23
    -repeat
    0.23
    Activations Density 0.008%

    No Known Activations