© 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. 24-TRANSCODER-HP
    7. 151226
    Prev
    Next
    INDEX
    Explanations

    Reviews and testimonials

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     scram
    -0.28
    mü
    -0.26
    andan
    -0.26
    ongoose
    -0.25
     taught
    -0.25
    å½»
    -0.25
    _sd
    -0.25
    rá
    -0.25
    und
    -0.24
     NSA
    -0.24
    POSITIVE LOGITS
     testimonials
    0.46
     testimon
    0.40
     endorsements
    0.40
    imonial
    0.40
    好è¯Ħ
    0.39
     endorsement
    0.37
    åı£ç¢ij
    0.36
    imonials
    0.36
     Yelp
    0.34
     Reviews
    0.31
    Activations Density 1.076%

    No Known Activations