© 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. 96288
    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
    俾
    -0.27
    æ¯įåħ¬åı¸
    -0.26
    rud
    -0.26
    çĤĢ
    -0.25
    çĶ³
    -0.25
    ince
    -0.25
    -men
    -0.24
     Smarty
    -0.24
     gaz
    -0.24
    )<=
    -0.24
    POSITIVE LOGITS
    Explicit
    0.30
    weights
    0.29
     explicit
    0.27
    createCommand
    0.27
    axies
    0.27
    ptions
    0.26
     Explicit
    0.26
    ferences
    0.25
    weight
    0.25
     weights
    0.25
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.