© 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. 96129
    Prev
    Next
    INDEX
    Explanations

    code and technical documentation

    np_max-act-logits · gemini-2.0-flash
    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
    æł½
    -0.30
     mó
    -0.25
    ç§įæ¤į
    -0.25
     inspected
    -0.25
    cular
    -0.25
    ninger
    -0.24
    ForResource
    -0.24
    Contracts
    -0.24
    CardBody
    -0.24
    FTA
    -0.24
    POSITIVE LOGITS
    æŃ£
    0.29
    break
    0.26
    åĽ½å®¶
    0.26
    äºĶåħŃ
    0.24
    å±ħæ°ij
    0.24
     Pred
    0.23
    å¸ĿåĽ½
    0.23
    Summon
    0.23
     gros
    0.23
     nationality
    0.23
    Activations Density 0.100%

    No Known Activations