© 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. 151415
    Prev
    Next
    INDEX
    Explanations

    product descriptions/names

    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
    isable
    -0.26
    ivos
    -0.26
    named
    -0.26
    úb
    -0.25
    aida
    -0.25
    kit
    -0.25
     honour
    -0.25
    rets
    -0.25
    iamo
    -0.24
    itas
    -0.24
    POSITIVE LOGITS
     //================================================================
    0.27
    çİ©ç¬ij
    0.26
    çĭĻ
    0.26
    her
    0.25
     ÑģкоÑĢ
    0.24
    Bias
    0.23
     hydro
    0.23
    tere
    0.23
    stant
    0.23
     Mang
    0.22
    Activations Density 0.895%

    No Known Activations