© 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. 58028
    Prev
    Next
    INDEX
    Explanations

    –

    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
    ademic
    -0.27
    quests
    -0.26
    =").
    -0.25
    iaux
    -0.24
    (sid
    -0.24
    åIJĥæĥĬ
    -0.24
    ATAB
    -0.24
    наÑĤ
    -0.24
    wich
    -0.24
    =#{
    -0.23
    POSITIVE LOGITS
    åŃ©åŃIJçļĦ
    0.27
    åĬĿ
    0.26
    å¦Ĥæŀľæľī
    0.25
     poison
    0.24
    èĢħçļĦ
    0.24
    æľīæķĪ
    0.24
    被åijĬ
    0.23
    OrCreate
    0.23
    å«Įçĸij
    0.23
     wa
    0.23
    Activations Density 0.001%

    No Known Activations