© 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. 23091
    Prev
    Next
    INDEX
    Explanations

    semiconductor, transistors

    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
     TreeMap
    -0.25
    æ¹ĸæ³Ĭ
    -0.25
    âĹī
    -0.24
    oxy
    -0.24
    _HOR
    -0.24
    UF
    -0.24
     personally
    -0.24
    NA
    -0.24
    oen
    -0.23
     UserRepository
    -0.23
    POSITIVE LOGITS
     cards
    0.26
    à¸Ľà¸£à¸°à¸Īำ
    0.26
    éĹ¨æ§Ľ
    0.25
     плоÑī
    0.25
    .byte
    0.25
    è¿ĩ大
    0.25
    çij
    0.24
    preci
    0.24
    _derivative
    0.24
    }()↵
    0.24
    Activations Density 0.016%

    No Known Activations