© 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. 360
    Prev
    Next
    INDEX
    Explanations

    Scientific/Names

    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
    icare
    -0.28
    ear
    -0.27
     aspiration
    -0.25
    ifu
    -0.24
    -na
    -0.24
    iche
    -0.24
     Prior
    -0.23
    _dy
    -0.23
    ication
    -0.23
    -tab
    -0.22
    POSITIVE LOGITS
    åŀ«
    0.26
    çķĻ
    0.25
    à¤
    0.25
    ugh
    0.25
     preliminary
    0.24
    @m
    0.24
    èĤļ
    0.24
     otherwise
    0.24
    æĶ»çķ¥
    0.23
     misses
    0.23
    Activations Density 0.486%

    No Known Activations