© 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. 33-TRANSCODER-HP
    7. 53318
    Prev
    Next
    INDEX
    Explanations

    technical text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -go
    -0.30
    è¯ģ
    -0.29
    ili
    -0.28
     ili
    -0.27
    msp
    -0.26
    «
    -0.26
    èŃī
    -0.26
    .go
    -0.24
    nte
    -0.24
    ilia
    -0.24
    POSITIVE LOGITS
    shal
    0.30
    adol
    0.28
    angent
    0.27
    è¿Ļä¸ĢçĤ¹
    0.26
    ual
    0.25
    ç£ģ
    0.25
    ue
    0.25
    relude
    0.24
    å°º
    0.24
    è¿ĻçĤ¹
    0.24
    Activations Density 0.121%

    No Known Activations