© 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. 130062
    Prev
    Next
    INDEX
    Explanations

    Instagram

    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
    AGMA
    -0.26
     Ikea
    -0.26
    æĪªæŃ¢
    -0.24
    å®ī康
    -0.23
    MAP
    -0.23
    æĮĤ
    -0.23
     PMC
    -0.23
     consolidated
    -0.23
     Cheney
    -0.23
    -Cs
    -0.22
    POSITIVE LOGITS
    sville
    0.30
    FAILURE
    0.27
    ly
    0.26
    ships
    0.24
    uur
    0.24
    wort
    0.24
    ivas
    0.23
     Fourth
    0.23
    @a
    0.23
    åħ±åĴĮåĽ½
    0.23
    Activations Density 0.019%

    No Known Activations