© 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. 27-TRANSCODER-HP
    7. 9337
    Prev
    Next
    INDEX
    Explanations

    compression

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĽĨåĽ¢èĤ¡ä»½
    -0.28
    ÂŃtion
    -0.27
    强迫
    -0.27
    è¯ī
    -0.26
    ution
    -0.26
    ä¸Ģç«Ļ
    -0.25
    axon
    -0.25
    以èī²
    -0.24
    ä¸Ģå¹ķ
    -0.24
    å¾Ģä¸ĭ
    -0.24
    POSITIVE LOGITS
    æ§ĥ
    0.28
    cord
    0.26
    olta
    0.25
    fahren
    0.24
    olv
    0.24
    ilm
    0.24
    foundland
    0.24
    <dim
    0.23
    ament
    0.23
    kn
    0.23
    Activations Density 0.004%

    No Known Activations