© 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. 95547
    Prev
    Next
    INDEX
    Explanations

    species

    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
    é¼ĵ
    -0.27
    systems
    -0.26
    ascus
    -0.26
    çĪ¸
    -0.26
    åģĩ
    -0.25
    imiter
    -0.25
    Mother
    -0.25
    çĪ¶äº²
    -0.25
    yme
    -0.24
    basename
    -0.24
    POSITIVE LOGITS
     species
    0.42
    çī©ç§į
    0.33
    Species
    0.33
    species
    0.32
    -spec
    0.32
     Species
    0.32
    nant
    0.29
     global
    0.29
    çºĮ
    0.29
    æľĢåIJİ
    0.29
    Activations Density 0.884%

    No Known Activations