© 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. 96017
    Prev
    Next
    INDEX
    Explanations

    Code files

    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
     skills
    -0.36
     methods
    -0.32
     Skills
    -0.31
     Methods
    -0.29
     techniques
    -0.29
    .methods
    -0.29
    ative
    -0.28
    getMethod
    -0.28
    Methods
    -0.27
    METHOD
    -0.27
    POSITIVE LOGITS
    DDS
    0.27
     nurs
    0.27
     <*
    0.26
     Axis
    0.26
    infinity
    0.26
     sint
    0.26
    ña
    0.26
     guarded
    0.25
     dt
    0.25
    ="//
    0.25
    Activations Density 0.891%

    No Known Activations