© 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. 149139
    Prev
    Next
    INDEX
    Explanations

    remember

    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
    -figure
    -0.26
    ainers
    -0.26
    allows
    -0.25
    izontal
    -0.25
    ån
    -0.23
    iken
    -0.23
    odial
    -0.23
    æĿ°åĩº
    -0.23
    anonymous
    -0.23
    orrh
    -0.23
    POSITIVE LOGITS
     trips
    0.30
     those
    0.30
    å½ĵæŶçļĦ
    0.28
    íĸī
    0.27
    rive
    0.27
     having
    0.26
    åľº
    0.26
     trip
    0.26
    ancia
    0.26
    çĶ¦
    0.26
    Activations Density 0.068%

    No Known Activations