© 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. 8669
    Prev
    Next
    INDEX
    Explanations

    loss

    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
    ç³»
    -0.30
     Nicholson
    -0.29
    sı
    -0.26
    spot
    -0.26
    ts
    -0.25
    èĥ½æī¾åĪ°
    -0.25
    acob
    -0.25
    ndon
    -0.24
    ODE
    -0.24
    èĥŀ
    -0.24
    POSITIVE LOGITS
    (es
    0.30
    fully
    0.29
    èĴ¯
    0.27
     incurred
    0.26
    es
    0.26
    ional
    0.25
    å¹´æĿ¥
    0.25
    esz
    0.25
    家åħ¬åı¸
    0.25
    imas
    0.24
    Activations Density 0.059%

    No Known Activations