© 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. 23714
    Prev
    Next
    INDEX
    Explanations

    Starting a new concept

    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
    adies
    -0.28
    apse
    -0.26
    æ¶Īè´¹éľĢæ±Ĥ
    -0.26
    åłª
    -0.25
    è
    -0.24
    inux
    -0.24
    asted
    -0.24
    enze
    -0.24
     demographic
    -0.23
     tapped
    -0.23
    POSITIVE LOGITS
    ç»į
    0.32
    essor
    0.28
    ôt
    0.27
     Giov
    0.26
    -depth
    0.25
     experts
    0.25
    åĩºçİ°åľ¨
    0.25
    ↵↵↵↵
    0.24
    Appearance
    0.23
    orio
    0.23
    Activations Density 0.000%

    No Known Activations