© 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. 95648
    Prev
    Next
    INDEX
    Explanations

    in

    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
    座
    -0.28
     INLINE
    -0.27
    opsy
    -0.26
    èĥ´
    -0.26
    bsites
    -0.25
    æĸ¹å¼ıè¿Ľè¡Į
    -0.24
    åħļæĢ»æĶ¯
    -0.24
    _process
    -0.23
    ãģĭãĤĬ
    -0.23
    INLINE
    -0.23
    POSITIVE LOGITS
    åıijå¸ĥ
    0.36
     prepared
    0.35
     a
    0.32
    åĩĨå¤ĩ
    0.30
    åħ±åIJĮ
    0.30
    åıijå¸ĥçļĦ
    0.30
    prepared
    0.29
     releasing
    0.28
     the
    0.28
     released
    0.28
    Activations Density 0.005%

    No Known Activations