© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 89679
    Prev
    Next
    INDEX
    Explanations

    Buffer

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ten
    -0.07
     entonces
    -0.07
     az
    -0.07
    tempt
    -0.07
    Donate
    -0.06
     Artifact
    -0.06
    노
    -0.06
     carrier
    -0.06
     xuân
    -0.06
    👹
    -0.06
    POSITIVE LOGITS
    缓冲
    0.09
     buffer
    0.08
    Buffer
    0.07
    .DEFAULT
    0.07
     substr
    0.07
     초기
    0.07
    	GL
    0.07
    𝚄
    0.07
    ирование
    0.07
     mixing
    0.07
    Activations Density 0.013%

    No Known Activations