© 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. 9271
    Prev
    Next
    INDEX
    Explanations

    Code/markup snippets

    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
    rig
    -0.30
    beck
    -0.27
    fires
    -0.26
    åŁ¹åħ»
    -0.26
    bor
    -0.26
     arma
    -0.25
    iness
    -0.25
    ERING
    -0.25
    hear
    -0.24
    FromFile
    -0.23
    POSITIVE LOGITS
    atics
    0.28
     Truth
    0.27
     stanza
    0.26
     rhyme
    0.25
    _Cl
    0.25
    åij¼åºĶ
    0.24
     keyword
    0.24
    keyword
    0.24
    -pay
    0.24
    .disconnect
    0.23
    Activations Density 0.003%

    No Known Activations