© 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. 20-TRANSCODER-HP
    7. 129585
    Prev
    Next
    INDEX
    Explanations

    creation, computers, or working hands

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arga
    -0.32
    ÄĻb
    -0.28
    ÑģÑĤÑĢой
    -0.27
    oplast
    -0.26
    Prev
    -0.26
    å°±åı¯ä»¥äºĨ
    -0.24
    æĭĺçķĻ
    -0.24
     entertain
    -0.24
    _compat
    -0.24
    们éĥ½
    -0.23
    POSITIVE LOGITS
    unden
    0.28
    umpt
    0.28
    çī©
    0.28
    åįļçī©
    0.27
    称ä¹ĭ
    0.26
    BY
    0.25
    ied
    0.25
    áŀı
    0.25
    TOT
    0.25
    å®ļ
    0.25
    Activations Density 10.863%

    No Known Activations