© 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. 23-TRANSCODER-HP
    7. 163109
    Prev
    Next
    INDEX
    Explanations

    Gold

    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
    åħļé£İ
    -0.27
    æĬµ
    -0.26
    åĮºæĶ¿åºľ
    -0.24
    æݥ管
    -0.24
    ifest
    -0.24
     getContext
    -0.24
    .rpm
    -0.24
    èĥ¥
    -0.24
    绥
    -0.24
    sov
    -0.23
    POSITIVE LOGITS
    s
    0.36
    leaf
    0.26
     deposit
    0.25
    -ste
    0.25
     mining
    0.25
    berries
    0.25
    -orange
    0.25
    -w
    0.24
    -pl
    0.24
    -green
    0.24
    Activations Density 0.251%

    No Known Activations