© 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. 108452
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     dung
    -0.27
    ãĤ¸ãĥ¥
    -0.26
     synt
    -0.25
    è¿Ļå°±
    -0.25
    ä¸īä½įä¸Ģä½ĵ
    -0.25
    ä¸Ģ件äºĭæĥħ
    -0.24
     trivia
    -0.24
    çĴĭ
    -0.24
    .semantic
    -0.24
    çģµæĦŁ
    -0.24
    POSITIVE LOGITS
    western
    0.26
    ige
    0.25
    egra
    0.25
    adge
    0.25
    assage
    0.25
    est
    0.24
     Emb
    0.24
    ipel
    0.24
    çķ²
    0.23
    getCode
    0.23
    Activations Density 0.899%

    No Known Activations

    This feature has no known activations.