© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 160
    Prev
    Next
    INDEX
    Explanations

    time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edException
    -0.31
     clipping
    -0.28
    æªIJ
    -0.26
    çļĦ身影
    -0.25
     shadows
    -0.25
    .SEVER
    -0.25
     dressing
    -0.25
    Ñģла
    -0.25
    ieties
    -0.24
    leÅŁtir
    -0.24
    POSITIVE LOGITS
    apter
    0.29
    åıĹ害èĢħ
    0.27
    uche
    0.27
    .resources
    0.27
     land
    0.27
    em
    0.24
    æĪ¾
    0.24
    ,...↵
    0.24
    )y
    0.23
    çķı
    0.23
    Activations Density 3.758%

    No Known Activations