© 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. 35-TRANSCODER-HP
    7. 39813
    Prev
    Next
    INDEX
    Explanations

    gibberish-related code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     backers
    -0.27
     dissent
    -0.26
     departed
    -0.26
     Escorts
    -0.26
     somebody
    -0.25
    åıĪæĺ¯
    -0.25
    SOAP
    -0.25
    inherits
    -0.25
     pops
    -0.25
    å¼ĢåĬŀ
    -0.24
    POSITIVE LOGITS
    roi
    0.44
    gi
    0.41
    zi
    0.39
    sei
    0.37
    ichi
    0.37
    ziel
    0.36
    pei
    0.36
    ugi
    0.35
    rei
    0.35
    gie
    0.35
    Activations Density 5.078%

    No Known Activations