© 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. 31-TRANSCODER-HP
    7. 19407
    Prev
    Next
    INDEX
    Explanations

    something is happening

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RIX
    -0.28
    ertools
    -0.28
    ç£ģ
    -0.28
    OTOS
    -0.28
    verture
    -0.28
    声
    -0.27
     magnetic
    -0.27
    ERSION
    -0.27
     cannon
    -0.27
     Magnetic
    -0.26
    POSITIVE LOGITS
     occurring
    0.36
     happening
    0.36
     real
    0.35
     occ
    0.32
     Occ
    0.32
    Real
    0.30
    åıijçĶŁ
    0.30
    _Real
    0.29
    åĬłå¿«å»ºè®¾
    0.28
     Real
    0.28
    Activations Density 0.979%

    No Known Activations