© 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. 108681
    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
    иÑĪ
    -0.28
    y
    -0.28
    ê±´
    -0.27
    dont
    -0.26
    交
    -0.26
    yd
    -0.26
    endregion
    -0.26
    S
    -0.26
     spell
    -0.25
    缸åħ³åĨħ容
    -0.25
    POSITIVE LOGITS
    ãĥĭãĥ³ãĤ°
    0.29
    å¼¥
    0.27
    æµij
    0.27
    arming
    0.26
     enumerated
    0.25
    汩
    0.25
    Ral
    0.25
    ]}</
    0.25
     Qing
    0.25
    QRST
    0.24
    Activations Density 0.317%

    No Known Activations

    This feature has no known activations.