© 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. 33-TRANSCODER-HP
    7. 53841
    Prev
    Next
    INDEX
    Explanations

    stories of people

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ±²åıĸ
    -0.29
    ä»İä¸Ń
    -0.26
    åı½
    -0.24
    chair
    -0.24
     оÑĤз
    -0.23
    åĨ³
    -0.23
    assin
    -0.23
    æ§Ľ
    -0.23
    aland
    -0.23
    ESSAGES
    -0.23
    POSITIVE LOGITS
     followed
    0.37
     preferred
    0.28
    ä¸Ģ代
    0.28
    WithOptions
    0.28
     setC
    0.27
    idential
    0.27
    端
    0.27
    骢
    0.26
    é£İéĻ©
    0.26
     risk
    0.26
    Activations Density 0.031%

    No Known Activations