© 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. 25-TRANSCODER-HP
    7. 109058
    Prev
    Next
    INDEX
    Explanations

    locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reached
    -0.27
     deductions
    -0.26
     anonymity
    -0.25
    è¾IJå°Ħ
    -0.25
     impunity
    -0.25
    ÙĦÙĬÙĥ
    -0.24
    èĬ¾
    -0.24
    /feed
    -0.24
     Fees
    -0.24
    èĥ½åĬĽåĴĮ
    -0.24
    POSITIVE LOGITS
    ä¸ĬçļĦ
    0.29
     breath
    0.28
    åij½
    0.26
    cken
    0.26
    ä¸Ĭ
    0.26
    ä¸ŃçļĦ
    0.26
     tin
    0.26
    otten
    0.25
    etri
    0.25
    enth
    0.25
    Activations Density 0.980%

    No Known Activations