© 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. 32-TRANSCODER-HP
    7. 42022
    Prev
    Next
    INDEX
    Explanations

    cache

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     naw
    -0.26
    RATION
    -0.26
    ãĥ©ãĥ³ãĥī
    -0.25
     succ
    -0.24
    éĺµéĺµ
    -0.24
    ä¸Ĭåīį
    -0.24
    acher
    -0.24
    succ
    -0.24
    æĶ¹éĿ©åıijå±ķ
    -0.24
    管çIJĨä¸Ńå¿ĥ
    -0.23
    POSITIVE LOGITS
     invalid
    0.35
    -invalid
    0.32
    invalid
    0.30
     Invalid
    0.29
    store
    0.29
    Invalid
    0.27
     co
    0.27
    åŀĤ
    0.26
    isValid
    0.26
    åħ±æľī
    0.26
    Activations Density 0.012%

    No Known Activations