© 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. 23474
    Prev
    Next
    INDEX
    Explanations

    How things work/are used

    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
    ãĥ¼ãĤ·ãĥ§ãĥ³
    -0.30
    åı¯çĶ¨äºİ
    -0.29
    Protocol
    -0.26
    åħĪ
    -0.25
     altern
    -0.24
    æĪĸå¤ļ
    -0.24
     SetLastError
    -0.24
    ItemAt
    -0.24
    ificates
    -0.23
    LAST
    -0.23
    POSITIVE LOGITS
    utory
    0.29
     Trad
    0.27
    à¸Ħà¸Ńม
    0.27
    rador
    0.26
     McCoy
    0.26
    产çī©
    0.25
    ä¸ŃåĽ½åı¤ä»£
    0.25
    atron
    0.25
    åı¤
    0.24
     Vid
    0.24
    Activations Density 0.001%

    No Known Activations