© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 107175
    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
    Negative Logits
    å°ıæŶåĨħ
    -0.27
    éĻįèĩ³
    -0.27
    rouch
    -0.26
    éĢļè¿ĩ
    -0.26
    .isSuccessful
    -0.26
    å³»
    -0.26
    ami
    -0.24
    éĻįåĪ°
    -0.24
    UES
    -0.24
    表çݰ为
    -0.24
    POSITIVE LOGITS
    ischer
    0.29
    aybe
    0.27
     underage
    0.27
    PickerController
    0.26
     nowhere
    0.25
     inev
    0.25
    æĵģ
    0.25
    æ¤ħ
    0.25
    erate
    0.24
     embarrassment
    0.24
    Activations Density 0.890%

    No Known Activations

    This feature has no known activations.