© 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. 39009
    Prev
    Next
    INDEX
    Explanations

    ph/oph

    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
    æ®ĭ
    -0.27
    ç»Ħç»ĩé¢Ĩ导
    -0.25
    åį«çĶŁ
    -0.25
    åıĪæĺ¯
    -0.24
    å¸Ĥå§Ķ书记
    -0.24
     Baron
    -0.23
    ç½
    -0.23
    顶
    -0.23
    dbus
    -0.23
    Baby
    -0.23
    POSITIVE LOGITS
    ag
    0.40
    agi
    0.37
    aging
    0.31
    acle
    0.31
    аг
    0.30
    iv
    0.29
    AG
    0.29
    agina
    0.29
    ited
    0.29
    imo
    0.29
    Activations Density 5.582%

    No Known Activations