© 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. 57827
    Prev
    Next
    INDEX
    Explanations

    Google URLs

    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
     ден
    -0.26
    Torrent
    -0.26
    adero
    -0.25
     бил
    -0.25
    ónico
    -0.24
    _EMIT
    -0.24
    ä¸Ģç»ı
    -0.24
    Ħ件
    -0.24
     getLogger
    -0.24
    <TSource
    -0.23
    POSITIVE LOGITS
     conv
    0.32
    åŁºç¡ĢçŁ¥è¯Ĩ
    0.27
     wound
    0.27
     verbs
    0.27
     erg
    0.26
    _conv
    0.24
     island
    0.24
     accessible
    0.24
    verbs
    0.24
     Mob
    0.24
    Activations Density 0.004%

    No Known Activations