© 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. 33-TRANSCODER-HP
    7. 53849
    Prev
    Next
    INDEX
    Explanations

    contains "č"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     \\↵
    -0.33
    \",↵
    -0.32
    \">↵
    -0.29
     \↵
    -0.27
    è¦ģä¸įçĦ¶
    -0.26
    ä»ĭç»įä¸Ģä¸ĭ
    -0.26
    çľĭä¸Ģçľĭ
    -0.25
    /';↵
    -0.24
    '+↵
    -0.24
    /";↵
    -0.23
    POSITIVE LOGITS
    č↵č↵
    0.50
    ...č↵
    0.46
    .č↵
    0.45
    ãĢĤč↵
    0.43
    č↵
    0.42
    .č↵č↵
    0.42
    č
    0.42
    !č↵
    0.41
    :č↵
    0.41
    ()č↵
    0.41
    Activations Density 0.005%

    No Known Activations