© 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. 24-TRANSCODER-HP
    7. 149579
    Prev
    Next
    INDEX
    Explanations

    Blog posts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     withStyles
    -0.28
    æŃ¡
    -0.26
    é²ij
    -0.26
    ãĤŃãĥ³
    -0.25
    nels
    -0.25
    SWG
    -0.24
    çĪ¶åŃIJ
    -0.24
    欢
    -0.24
    Å°
    -0.24
    ewriter
    -0.24
    POSITIVE LOGITS
     world
    0.31
    ä¸ĸçķĮ
    0.29
    Ĺı
    0.29
     Worlds
    0.28
     ecosystem
    0.27
    çłĶ
    0.26
    indh
    0.25
    ä¸ĸçķĮçļĦ
    0.25
    管åĪ¶
    0.25
    ac
    0.25
    Activations Density 0.146%

    No Known Activations