© 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. 7-RESID-POST-AA
    11. 9665
    Prev
    Next
    INDEX
    Explanations

    code/configuration files

    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
     �
    -0.07
     terminates
    -0.07
    enes
    -0.07
     personas
    -0.07
    גולשים
    -0.07
    unes
    -0.07
    .exchange
    -0.07
    -collar
    -0.07
    anium
    -0.07
     afs
    -0.07
    POSITIVE LOGITS
     Joey
    0.08
    わず
    0.08
    سوف
    0.07
     décid
    0.07
     Bob
    0.07
     surviv
    0.07
    didn
    0.07
     أن
    0.07
    keep
    0.07
    iği
    0.07
    Activations Density 0.003%

    No Known Activations