© 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. 30-TRANSCODER-HP
    7. 96254
    Prev
    Next
    INDEX
    Explanations

    names and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cast
    -0.34
    æī«
    -0.32
    aps
    -0.29
     combining
    -0.28
     rat
    -0.27
    触åıĬ
    -0.27
    女åıĭ
    -0.27
    Cast
    -0.26
    cast
    -0.26
    å°ĺ
    -0.26
    POSITIVE LOGITS
    licos
    0.27
     agreg
    0.26
    ira
    0.26
     Petty
    0.26
     HRESULT
    0.25
    iration
    0.25
    ETING
    0.25
    imers
    0.24
    ihn
    0.24
    áng
    0.24
    Activations Density 0.001%

    No Known Activations