© 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. 98291
    Prev
    Next
    INDEX
    Explanations

    Generated text / forum posts

    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
    uetype
    -0.26
    prs
    -0.24
    ests
    -0.24
    ugo
    -0.23
    imates
    -0.23
    èĢĮåİ»
    -0.23
    SharedPtr
    -0.23
    formatter
    -0.23
    uais
    -0.23
    è¯ł
    -0.23
    POSITIVE LOGITS
     openings
    0.27
    spawn
    0.25
    Ñģан
    0.24
    sonian
    0.24
    sein
    0.23
    éű
    0.23
    _Unit
    0.23
     Schön
    0.23
     cur
    0.22
    åĭĥåĭĥ
    0.22
    Activations Density 0.000%

    No Known Activations