© 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. 22-TRANSCODER-HP
    7. 129325
    Prev
    Next
    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pei
    -0.27
    lemma
    -0.26
     Fisher
    -0.25
    éĢĤ
    -0.24
    switch
    -0.24
    proc
    -0.24
    _products
    -0.24
    Firebase
    -0.24
    产åĵģç»ıçIJĨ
    -0.24
    åįĩ级
    -0.24
    POSITIVE LOGITS
    otonin
    0.27
    å®īç½®
    0.26
     Bibli
    0.25
    ÑĤÑı
    0.25
    çĵ¢
    0.25
     rif
    0.25
    برا
    0.24
     CARE
    0.24
    éĶı
    0.24
    ltr
    0.23
    Activations Density 0.091%

    No Known Activations