© 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. 280
    Prev
    Next
    INDEX
    Explanations

    e

    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
    ä¸įæŃ»
    -0.27
    /header
    -0.25
    åıĪ好
    -0.24
    ÑģÑĤво
    -0.24
    mere
    -0.24
    交æį¢
    -0.24
    çĭ
    -0.23
    ifter
    -0.23
    è¶Ĭ好
    -0.23
    许åı¯
    -0.23
    POSITIVE LOGITS
    dee
    0.27
    anonymous
    0.26
     desn
    0.24
     fals
    0.24
    iner
    0.24
    entially
    0.23
     fortunately
    0.23
    åħ³äºİæĪij们
    0.23
    .thumbnail
    0.23
    æ·±åĪĩ
    0.23
    Activations Density 0.768%

    No Known Activations