© 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. 95546
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     Swedish
    -0.28
     semantic
    -0.24
    sem
    -0.24
     bet
    -0.24
    èĬĤ
    -0.24
    vet
    -0.24
     dzie
    -0.24
    宽
    -0.24
    éĻĽä¸ĭ
    -0.24
    çijŀåħ¸
    -0.23
    POSITIVE LOGITS
    ories
    0.28
    ikel
    0.27
    itude
    0.27
    UCK
    0.25
    itative
    0.25
    wealth
    0.25
    елÑı
    0.24
     Tau
    0.24
     Approach
    0.24
    itura
    0.24
    Activations Density 0.002%

    No Known Activations