© 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. 25-TRANSCODER-HP
    7. 108368
    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_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åħħè£ķ
    -0.28
    rix
    -0.28
    èĶļ
    -0.27
    ä¿Ŀéļª
    -0.24
    arel
    -0.24
    _SUITE
    -0.24
     fuel
    -0.23
    bü
    -0.23
    è¤Ĭ
    -0.23
    ALE
    -0.23
    POSITIVE LOGITS
    ä»°
    0.28
    è´§
    0.26
    bor
    0.26
    гоÑĢод
    0.26
    å·¥
    0.26
    éĶIJ
    0.25
     materials
    0.25
     Guinea
    0.25
    igon
    0.25
    materials
    0.25
    Activations Density 0.912%

    No Known Activations