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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RESID-POST-AA
    11. 21870
    Prev
    Next
    INDEX
    Explanations

    ING

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Car
    -0.07
     earnings
    -0.07
     wool
    -0.07
    Solution
    -0.07
    Pro
    -0.07
    Begin
    -0.06
    .puts
    -0.06
     Pine
    -0.06
     nomin
    -0.06
    zure
    -0.06
    POSITIVE LOGITS
    意义上
    0.08
    .SimpleDateFormat
    0.08
     ville
    0.08
     componentName
    0.08
     cliente
    0.07
    ﻒ
    0.07
    роме
    0.07
    (color
    0.07
     "?"
    0.07
    ей
    0.07
    Activations Density 0.146%

    No Known Activations