© 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. 32-TRANSCODER-HP
    7. 43534
    Prev
    Next
    INDEX
    Explanations

    Technical language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    »¿
    -0.28
    xp
    -0.26
     cap
    -0.26
    ys
    -0.26
    ra
    -0.26
    regon
    -0.25
     identity
    -0.25
    ×ŀ×Ļ
    -0.25
    pd
    -0.25
    -uppercase
    -0.25
    POSITIVE LOGITS
    egov
    0.28
    ICO
    0.26
     Patreon
    0.25
    Father
    0.24
    èĺħ
    0.24
     hoops
    0.23
     enumeration
    0.23
    -Javadoc
    0.23
     PACKAGE
    0.23
    没è§ģè¿ĩ
    0.23
    Activations Density 0.000%

    No Known Activations