© 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. 35-TRANSCODER-HP
    7. 39390
    Prev
    Next
    INDEX
    Explanations

    software license

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĩ³å°ij
    -0.30
     correct
    -0.30
    æĪIJåĬŁçļĦ
    -0.28
    ej
    -0.27
    å®Įåħ¨
    -0.26
     Correct
    -0.26
    è§Ĩ
    -0.25
     Successfully
    -0.25
     atleast
    -0.25
     surely
    -0.24
    POSITIVE LOGITS
     textual
    0.27
    ket
    0.26
     bil
    0.25
    ODY
    0.25
     retaliation
    0.24
     online
    0.24
     epis
    0.24
    uments
    0.24
     logical
    0.23
     textColor
    0.23
    Activations Density 8.978%

    No Known Activations