© 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. 96449
    Prev
    Next
    INDEX
    Explanations

    technical/formal documents

    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
    iVar
    -0.27
    è¶ĬãģĹ
    -0.26
    -stream
    -0.26
    ä¸Ńè¶ħ
    -0.26
    ecz
    -0.26
    over
    -0.25
    ighted
    -0.25
    .mouse
    -0.25
    ocaust
    -0.25
    andom
    -0.24
    POSITIVE LOGITS
     alt
    0.28
    arp
    0.26
    ä¸Ģå¼ł
    0.26
     pairing
    0.25
    ugs
    0.25
    è¡Į车
    0.25
    éĺ³
    0.24
    _direction
    0.24
    upp
    0.24
    ista
    0.24
    Activations Density 0.865%

    No Known Activations