© 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. 8919
    Prev
    Next
    INDEX
    Explanations

    one

    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
    ovation
    -0.30
    éĶı
    -0.28
    agine
    -0.26
    ",@"
    -0.25
    ÑĤи
    -0.24
    åĭĭ
    -0.24
    çİ°çĬ¶
    -0.24
    uing
    -0.24
    Aura
    -0.24
    \P
    -0.24
    POSITIVE LOGITS
     of
    0.41
     thereof
    0.34
    à¸Ĥà¸Ńà¸ĩ
    0.31
    of
    0.29
     Bolt
    0.27
     bolts
    0.27
     của
    0.26
     dates
    0.25
     sectors
    0.25
     traces
    0.24
    Activations Density 0.044%

    No Known Activations