© 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. 58021
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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
    rees
    -0.29
    容
    -0.27
    resses
    -0.26
    åŁİå¸Ĥ管çIJĨ
    -0.26
    ropa
    -0.25
    åĩĨæŶ
    -0.24
    Participant
    -0.24
    ersh
    -0.24
    å¼Ģ
    -0.24
    unities
    -0.24
    POSITIVE LOGITS
    htar
    0.36
    oxy
    0.27
     talks
    0.26
     Paleo
    0.26
    èµ°åľ¨
    0.25
    æĹłè¾ľ
    0.25
    год
    0.24
    éħ£
    0.24
    åħ¬
    0.24
    éªħ
    0.24
    Activations Density 0.091%

    No Known Activations