© 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. 179
    Prev
    Next
    INDEX
    Explanations

    revisions

    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
    edImage
    -0.25
    .deploy
    -0.25
    _legal
    -0.24
    edd
    -0.24
    },'
    -0.23
    ilyn
    -0.23
     Plex
    -0.23
    annie
    -0.23
    éªĬ
    -0.23
    childs
    -0.23
    POSITIVE LOGITS
    æĪij们ä¼ļ
    0.30
    ars
    0.27
     footsteps
    0.26
    åĵŁ
    0.26
    GS
    0.25
    ä¸ĸçķĮè§Ĥ
    0.25
    ¢åįķ
    0.25
     Heads
    0.24
    GP
    0.24
    erm
    0.24
    Activations Density 0.047%

    No Known Activations