© 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. 39367
    Prev
    Next
    INDEX
    Explanations

    Medical/chemical text

    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
    áticas
    -0.29
    ionate
    -0.29
    istr
    -0.28
    ikes
    -0.28
    it
    -0.27
    utorial
    -0.26
    otypes
    -0.26
    itive
    -0.26
    iously
    -0.26
    omorphic
    -0.25
    POSITIVE LOGITS
    nce
    0.40
    nge
    0.39
     nal
    0.35
    ncy
    0.35
    nie
    0.35
    lla
    0.32
    nze
    0.32
    nd
    0.32
    DDL
    0.32
    ssa
    0.31
    Activations Density 4.014%

    No Known Activations