© 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. 24-TRANSCODER-HP
    7. 150516
    Prev
    Next
    INDEX
    Explanations

    organizational missions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ereal
    -0.28
    arty
    -0.27
    å¸ĥå±Ģ
    -0.27
    orns
    -0.26
    京津
    -0.26
     UIL
    -0.24
     continental
    -0.24
    اخ
    -0.24
    accessible
    -0.24
    .Layout
    -0.23
    POSITIVE LOGITS
    å®Ŀçİī
    0.29
     besten
    0.28
     gcd
    0.28
    bé
    0.26
    _ctr
    0.26
    诸èijĽ
    0.26
    å½ĺ
    0.25
    InstanceState
    0.25
    ivan
    0.25
    onné
    0.25
    Activations Density 0.111%

    No Known Activations