© 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. 24-TRANSCODER-HP
    7. 150013
    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_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vents
    -0.27
    머
    -0.27
    mps
    -0.26
    头éĥ¨
    -0.26
     hô
    -0.26
     Ladies
    -0.25
    Tho
    -0.25
    imet
    -0.24
     heads
    -0.24
    riters
    -0.24
    POSITIVE LOGITS
    çļĩ
    0.27
    lush
    0.25
     transmission
    0.24
    产åĵģè´¨éĩı
    0.24
     unin
    0.24
    oufl
    0.24
    aint
    0.23
    éĵ¡
    0.23
    klär
    0.23
    олÑĮко
    0.23
    Activations Density 0.113%

    No Known Activations