© 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. 23-TRANSCODER-HP
    7. 24058
    Prev
    Next
    INDEX
    Explanations

    Unicode characters/encoding errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soever
    -0.29
    oga
    -0.26
     Paradise
    -0.25
    OffsetTable
    -0.25
    olders
    -0.25
    é³ħ
    -0.25
    hero
    -0.25
     sodom
    -0.24
     Sisters
    -0.24
     paradise
    -0.24
    POSITIVE LOGITS
    er
    0.32
    BAL
    0.28
    ly
    0.27
     ac
    0.26
    emer
    0.26
    rax
    0.26
    ä¸į平衡
    0.26
    l
    0.25
    r
    0.25
    B
    0.25
    Activations Density 0.109%

    No Known Activations