© 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. 27-TRANSCODER-HP
    7. 9180
    Prev
    Next
    INDEX
    Explanations

    Duration

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    peace
    -0.31
    计
    -0.29
     Rover
    -0.27
    tsy
    -0.27
    udit
    -0.27
     Newman
    -0.27
     peace
    -0.26
     faker
    -0.25
     stability
    -0.25
    creativecommons
    -0.25
    POSITIVE LOGITS
     Duration
    0.45
     durations
    0.44
     duration
    0.44
    duration
    0.43
    Duration
    0.36
    缩çŁŃ
    0.35
    _duration
    0.34
    	duration
    0.34
     mild
    0.34
    延éķ¿
    0.34
    Activations Density 0.026%

    No Known Activations