© 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. 149535
    Prev
    Next
    INDEX
    Explanations

    This

    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
    Not in Any Lists

    No Comments

    Negative Logits
    (#
    -0.26
     opi
    -0.26
    æıIJåıĬ
    -0.25
     pul
    -0.24
    above
    -0.24
     Shi
    -0.23
    æĢİä¹Īåģļ
    -0.23
    é¤ħ
    -0.23
    è§IJ
    -0.23
    eltas
    -0.23
    POSITIVE LOGITS
    çľĭçĶµå½±
    0.25
    æĺĤ
    0.25
    rail
    0.25
     IDC
    0.24
    æĦıåij³
    0.24
    çIJĨå·¥
    0.24
    ModelError
    0.24
    DK
    0.24
    åĪĨ
    0.24
    >//
    0.24
    Activations Density 0.145%

    No Known Activations