© 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. 39678
    Prev
    Next
    INDEX
    Explanations

    particulate matter

    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
    incerely
    -0.34
    spiel
    -0.30
    the
    -0.28
    GLOBALS
    -0.28
    tesy
    -0.27
    rick
    -0.27
    rebbe
    -0.27
    iÄĻ
    -0.27
    mapper
    -0.26
    ropolitan
    -0.26
    POSITIVE LOGITS
     poisoning
    0.33
     faults
    0.32
     synth
    0.32
     sulf
    0.30
     corros
    0.30
     masks
    0.30
     propagation
    0.30
     dissolution
    0.30
     cracks
    0.30
     diam
    0.30
    Activations Density 0.292%

    No Known Activations