© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7326
    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_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    缯
    -0.26
     pool
    -0.26
    æĺ¯æĢİä¹Ī
    -0.26
    æī¹åıijå¸Ĥåľº
    -0.25
    oenix
    -0.25
    åħ·ä½ĵçļĦ
    -0.25
    pool
    -0.24
    åIJ§
    -0.24
    sylvania
    -0.24
    ä¸Ģ声
    -0.24
    POSITIVE LOGITS
    ity
    0.27
    eli
    0.26
    ocker
    0.26
    åħĦå¼Ł
    0.25
    edList
    0.25
    Vel
    0.25
     Mey
    0.24
    ewing
    0.24
    cue
    0.24
    edBy
    0.24
    Activations Density 1.164%

    No Known Activations