© 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. 96445
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ãĤ»ãĥ³ãĤ¿ãĥ¼
    -0.27
     Euler
    -0.26
     van
    -0.26
    HttpException
    -0.26
     rh
    -0.26
    house
    -0.25
     inv
    -0.25
    cov
    -0.25
     rec
    -0.25
     run
    -0.24
    POSITIVE LOGITS
     tou
    0.26
    alic
    0.25
    ]<<
    0.25
    arel
    0.25
    alone
    0.25
    _Delay
    0.25
    移æ°ij
    0.24
    æĭĶ
    0.24
    uncan
    0.24
     Aless
    0.24
    Activations Density 0.004%

    No Known Activations