© 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. 54122
    Prev
    Next
    INDEX
    Explanations

    Sequences of `>` characters

    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
    åĩŃ
    -0.31
    ACHI
    -0.26
    æݧ
    -0.26
     coveted
    -0.26
    arios
    -0.25
    orado
    -0.25
     solar
    -0.25
    segments
    -0.24
    ë°°
    -0.24
    æĨij
    -0.24
    POSITIVE LOGITS
    >>
    0.55
    )>>
    0.52
     >>
    0.49
    >>&
    0.42
     plate
    0.42
    >>>>
    0.41
    >>>>>>>>
    0.41
    Plate
    0.40
    >>>
    0.39
    _plate
    0.39
    Activations Density 0.375%

    No Known Activations