© 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. 12-TRANSCODER-HP
    7. 23463
    Prev
    Next
    INDEX
    Explanations

    mass spectrometry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igers
    -0.28
    praak
    -0.25
     Nam
    -0.24
    æĹłåĬĽ
    -0.24
    semblies
    -0.24
    å®Įåħ¨
    -0.23
    Entr
    -0.23
     Perspectives
    -0.23
    .dk
    -0.23
     Ent
    -0.22
    POSITIVE LOGITS
    subtype
    0.30
     establishment
    0.30
    åħijçİ°
    0.29
    variably
    0.28
     negativity
    0.28
    condition
    0.27
     conformity
    0.26
    vat
    0.25
     conditioning
    0.24
    å¿Ĺ
    0.24
    Activations Density 0.022%

    No Known Activations