© 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. 107360
    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
    ouri
    -0.26
    å°º
    -0.26
    åħ¬å¼Ģåıijè¡Į
    -0.25
    cai
    -0.25
    anz
    -0.25
    ictory
    -0.25
    åħ¨éĿ¢å»ºæĪIJ
    -0.25
    对æĪij们
    -0.25
     Recru
    -0.24
    广éĺĶçļĦ
    -0.23
    POSITIVE LOGITS
    ç»ĵ
    0.29
    äºĴè¡¥
    0.26
    为空
    0.25
    /testing
    0.24
    alled
    0.23
    ÑİÑīие
    0.23
    çµIJ
    0.23
     Air
    0.23
    Alignment
    0.23
    adesh
    0.23
    Activations Density 0.889%

    No Known Activations

    This feature has no known activations.