© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 24452
    Prev
    Next
    INDEX
    Explanations

    methane

    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
    çĪ¶
    -0.28
    æIJĢ
    -0.27
    åĵ²åѦ
    -0.26
    inish
    -0.26
    ready
    -0.26
    orney
    -0.26
     aston
    -0.25
    evin
    -0.25
    ä¸īæĸ¹
    -0.25
     Metadata
    -0.25
    POSITIVE LOGITS
     natural
    0.26
    auté
    0.25
    uire
    0.25
    }-{
    0.25
    ãĥĭãĥ¥
    0.24
     clearance
    0.24
    лÑİ
    0.24
     livest
    0.24
     level
    0.24
    )-(
    0.24
    Activations Density 0.003%

    No Known Activations