© 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. 23101
    Prev
    Next
    INDEX
    Explanations

    Flickr

    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
    ério
    -0.30
    ucid
    -0.27
    elite
    -0.26
    ication
    -0.26
    cation
    -0.25
    icals
    -0.25
    emento
    -0.24
    ising
    -0.24
    ä¹Łè¶ĬæĿ¥è¶Ĭ
    -0.24
    KIT
    -0.24
    POSITIVE LOGITS
     Modifier
    0.25
    æľĭ
    0.24
    ember
    0.24
    modifier
    0.24
    ::$_
    0.24
     enrolled
    0.24
    íķĺ
    0.23
    çĭ¼
    0.23
    è¦ģè¿Ľä¸ĢæŃ¥
    0.23
    æĿľç»Ŀ
    0.23
    Activations Density 0.002%

    No Known Activations