© 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. 23-TRANSCODER-HP
    7. 24209
    Prev
    Next
    INDEX
    Explanations

    achs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ste
    -0.28
    åĽŀ头
    -0.26
    west
    -0.26
    ãĥı
    -0.25
     kat
    -0.25
    erts
    -0.24
    icina
    -0.24
     Har
    -0.24
    ä¹ĸä¹ĸ
    -0.24
     hob
    -0.24
    POSITIVE LOGITS
    nu
    0.33
    ndo
    0.32
    nty
    0.30
    nym
    0.29
    nı
    0.29
    nej
    0.28
    нÑĥ
    0.28
    nThe
    0.28
    ndata
    0.27
    NU
    0.27
    Activations Density 0.022%

    No Known Activations