© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 102973
    Prev
    Next
    INDEX
    Explanations

    Places and people

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocker
    -0.07
    можно
    -0.07
     toned
    -0.07
     gew
    -0.07
    مدر
    -0.06
    教材
    -0.06
     gg
    -0.06
     fellowship
    -0.06
    Winter
    -0.06
    .cloud
    -0.06
    POSITIVE LOGITS
     paralyzed
    0.07
    .device
    0.07
     	
    0.07
     Ethiopia
    0.07
     Relevant
    0.06
     Galactic
    0.06
     เมษายน
    0.06
     парти
    0.06
    רוג
    0.06
    參與
    0.06
    Activations Density 0.006%

    No Known Activations