© 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. 95893
    Prev
    Next
    INDEX
    Explanations

    nonsensical text

    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
    .Sm
    -0.26
    缴æµģ
    -0.26
     Immediately
    -0.26
    bery
    -0.25
    ç«ĭåį³
    -0.25
     Immediate
    -0.25
     Draws
    -0.25
     immediate
    -0.25
     Lesser
    -0.25
    çŀ¢
    -0.24
    POSITIVE LOGITS
    åłĤ
    0.27
    å¥ī
    0.26
     trom
    0.26
    åĩłå®¶
    0.25
    .bulk
    0.25
    Bulk
    0.24
    ä¾Ĺ
    0.24
    HEMA
    0.24
    >*/↵
    0.24
    -pills
    0.24
    Activations Density 0.000%

    No Known Activations