© 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. 35-TRANSCODER-HP
    7. 38809
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    çłĶåĪ¶
    -0.29
    asc
    -0.28
    dro
    -0.28
    éļIJç§ģ
    -0.28
    che
    -0.26
    bell
    -0.26
    esch
    -0.26
    æ£Ĵ
    -0.26
    bar
    -0.26
    çīĩ
    -0.25
    POSITIVE LOGITS
     htmlentities
    0.29
     htonl
    0.28
     TED
    0.26
     Remaining
    0.25
     IService
    0.25
     BaseService
    0.25
     Prosecutor
    0.24
     VERBOSE
    0.24
     Fucking
    0.24
     Guests
    0.24
    Activations Density 37.185%

    No Known Activations

    This feature has no known activations.