Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 131007
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    relations
    -0.08
    illac
    -0.07
     Julius
    -0.07
     precis
    -0.07
     isEqual
    -0.07
    criteria
    -0.07
    IsEmpty
    -0.07
     inequalities
    -0.07
    导读
    -0.07
    _attention
    -0.06
    POSITIVE LOGITS
    nız
    0.07
     AsyncStorage
    0.07
     foram
    0.07
    ᒼ
    0.07
    _VARS
    0.07
    ской
    0.07
    CKET
    0.07
    .FileOutputStream
    0.07
    ᠆
    0.07
    火箭
    0.07
    Activations Density 0.001%

    No Known Activations