© 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. 18-TRANSCODER-HP
    7. 89433
    Prev
    Next
    INDEX
    Explanations

    locations/directions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    attend
    -0.28
    æīĭ
    -0.26
     jar
    -0.25
    á»Ĥ
    -0.24
    éĢļ
    -0.24
    æĪIJ
    -0.24
    çļĦæīĭ
    -0.24
    {j
    -0.24
    åºıåĪĹ
    -0.23
    imer
    -0.23
    POSITIVE LOGITS
     location
    0.36
    è¿Ļä¸ªåľ°æĸ¹
    0.35
     LOCATION
    0.32
    ä½įäºİ
    0.32
     situated
    0.31
    (location
    0.30
     whereabouts
    0.30
    ä»Ģä¹Īåľ°æĸ¹
    0.30
    ä½ķå¤Ħ
    0.29
     located
    0.29
    Activations Density 59.855%

    No Known Activations