© 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. 23-TRANSCODER-HP
    7. 24750
    Prev
    Next
    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĿijéķĩ
    -0.29
     expectedResult
    -0.28
    å°¤åħ¶æĺ¯åľ¨
    -0.27
    å°¹
    -0.26
     Fond
    -0.24
    vpn
    -0.24
    çī¹åĪ«æĺ¯åľ¨
    -0.24
    åħ¸åŀĭæ¡Īä¾ĭ
    -0.24
    ican
    -0.23
    èѬå¦Ĥ
    -0.23
    POSITIVE LOGITS
     laat
    0.26
    èIJ½å®ŀ
    0.25
    اÙħت
    0.24
    owing
    0.23
    ание
    0.23
    çľīæ¯Ľ
    0.23
    è¿Ļä¸ĢåĪ»
    0.23
    án
    0.23
     mates
    0.23
    .sheet
    0.23
    Activations Density 0.003%

    No Known Activations