© 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. 27-TRANSCODER-HP
    7. 57351
    Prev
    Next
    INDEX
    Explanations

    Website and documentation text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ownload
    -0.28
    åıij
    -0.28
     intens
    -0.28
    é«®
    -0.26
     fits
    -0.25
    ideos
    -0.25
    å¹³åİŁ
    -0.25
     Ple
    -0.25
     beds
    -0.24
    Posted
    -0.24
    POSITIVE LOGITS
    æĥħåĨµè¿Ľè¡Į
    0.32
    UEST
    0.27
    æł·åŃIJ
    0.26
    zburg
    0.26
    æĥħåĨµ
    0.24
    çķĻè¨ĢæĿ¿
    0.24
    æĥħæĻ¯
    0.24
    skb
    0.24
    ueue
    0.24
     Sheridan
    0.24
    Activations Density 0.002%

    No Known Activations