© 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. 12-TRANSCODER-HP
    7. 22821
    Prev
    Next
    INDEX
    Explanations

    nutrition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĭĩäºİ
    -0.28
    cope
    -0.26
     Pad
    -0.24
    临
    -0.24
    acks
    -0.24
    箬
    -0.24
    çĪ¸
    -0.23
     nữa
    -0.23
     Aff
    -0.23
    _pad
    -0.23
    POSITIVE LOGITS
    merged
    0.28
     cockpit
    0.28
     merged
    0.27
     emulator
    0.26
    CORD
    0.26
     universe
    0.26
    ä¿¡æģ¯åıijå¸ĥ
    0.25
    >tag
    0.25
     proport
    0.25
    uner
    0.25
    Activations Density 0.022%

    No Known Activations