© 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. 33-TRANSCODER-HP
    7. 53103
    Prev
    Next
    INDEX
    Explanations

    def

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     def
    -0.30
    éĽį
    -0.29
    orial
    -0.27
    rale
    -0.26
    urally
    -0.25
    èħŃ
    -0.24
    def
    -0.24
    uras
    -0.24
    Æ¡
    -0.24
    ral
    -0.24
    POSITIVE LOGITS
     fore
    0.40
    fore
    0.39
    Fore
    0.38
     Fore
    0.37
    _fore
    0.33
    claimer
    0.32
    åħ»
    0.29
     fores
    0.28
    KIT
    0.28
     foreclosure
    0.28
    Activations Density 0.005%

    No Known Activations