© 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. 30-TRANSCODER-HP
    7. 96446
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     //č↵
    -0.28
     perch
    -0.26
    åIJįå½ķ
    -0.25
    foy
    -0.24
     subsequently
    -0.24
    //č↵
    -0.24
     Crawford
    -0.24
    åı¯èĥ½
    -0.24
    endforeach
    -0.23
     Daly
    -0.23
    POSITIVE LOGITS
    å±£
    0.29
    -version
    0.26
     pillows
    0.26
    fal
    0.25
     Saul
    0.25
    çĶ¨äºº
    0.25
     cushions
    0.24
    -solid
    0.24
     Power
    0.24
    veh
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.