© 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. 87
    Prev
    Next
    INDEX
    Explanations

    Picasso

    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
    Ĥ¬
    -0.28
    upe
    -0.28
     Strat
    -0.27
    epar
    -0.27
    ehr
    -0.26
    ovation
    -0.26
     density
    -0.25
     capacity
    -0.24
     fel
    -0.24
     av
    -0.24
    POSITIVE LOGITS
    åĬ³
    0.26
    atoon
    0.26
     Automatically
    0.26
    æ®ĭ
    0.26
     nipples
    0.25
    LM
    0.25
    :inline
    0.24
     tượng
    0.24
    ç²¾çĽĬæ±Ĥç²¾
    0.24
     Sweat
    0.24
    Activations Density 0.007%

    No Known Activations