© 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. 8710
    Prev
    Next
    INDEX
    Explanations

    able

    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
     ÏĢ
    -0.71
    ÏĢ
    -0.69
     pi
    -0.58
    pi
    -0.58
    .pi
    -0.56
    _pi
    -0.54
    (pi
    -0.54
    *pi
    -0.53
    ðĿľĭ
    -0.51
    _PI
    -0.49
    POSITIVE LOGITS
    å¹²
    0.32
    IDER
    0.28
     sweat
    0.28
     dry
    0.28
    iko
    0.28
    isko
    0.27
    èį£
    0.27
    DEX
    0.26
    anger
    0.26
     Dry
    0.26
    Activations Density 0.015%

    No Known Activations