© 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. 39032
    Prev
    Next
    INDEX
    Explanations

    Hacking and exploits

    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
    è¿ij
    -0.28
    建
    -0.28
    etal
    -0.27
    ล
    -0.26
     Close
    -0.26
     Collective
    -0.26
    ãĢĤï¼Ī
    -0.26
    绣
    -0.25
     Goals
    -0.25
    archs
    -0.25
    POSITIVE LOGITS
     falsely
    0.39
     unlaw
    0.39
    被éªĹ
    0.36
     s
    0.36
     slander
    0.35
    /epl
    0.35
     distrust
    0.35
     subpoena
    0.35
     unfairly
    0.34
     boyc
    0.34
    Activations Density 1.962%

    No Known Activations