© 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. 25-TRANSCODER-HP
    7. 107494
    Prev
    Next
    INDEX
    Explanations

    Rog

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ°ijéĹ´
    -0.27
     unset
    -0.27
     autof
    -0.26
     Summit
    -0.26
    _seen
    -0.25
    aso
    -0.25
    éĩįè§Ĩ
    -0.25
    æķ´æķ´
    -0.25
     embodiment
    -0.25
     ac
    -0.25
    POSITIVE LOGITS
    uers
    0.29
    ừa
    0.27
    _trade
    0.26
    trade
    0.26
    åİ¿åħ¬å®īå±Ģ
    0.26
    Trade
    0.25
    .sendStatus
    0.25
    _hs
    0.24
     pige
    0.24
    race
    0.24
    Activations Density 0.274%

    No Known Activations