© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 30-TRANSCODER-HP
    7. 95953
    Prev
    Next
    INDEX
    Explanations

    potential

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.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
    .isValid
    -0.26
     Urs
    -0.25
    å¹³åİŁ
    -0.25
     gÅĤówne
    -0.25
    欢
    -0.25
     scour
    -0.24
    erp
    -0.24
    ufact
    -0.24
    ctors
    -0.24
    POSITIVE LOGITS
     potential
    0.35
     latent
    0.29
     potentials
    0.28
    potential
    0.27
    æĥĬ人
    0.27
     combined
    0.27
    emann
    0.27
    endant
    0.27
     unique
    0.26
     true
    0.26
    Activations Density 0.105%

    No Known Activations