© 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. 29708
    Prev
    Next
    INDEX
    Explanations

    Emigration/Migration

    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
     inserted
    -0.08
     amore
    -0.07
     salope
    -0.07
    pv
    -0.07
     gigs
    -0.07
    ipel
    -0.07
     Detaylı
    -0.06
    中方
    -0.06
     considerations
    -0.06
    缓缓
    -0.06
    POSITIVE LOGITS
    #\
    0.07
    _cluster
    0.07
     PCA
    0.07
    LOC
    0.07
     Boulder
    0.07
    注册资本
    0.06
    总产值
    0.06
    GetProperty
    0.06
    ultureInfo
    0.06
     __________________
    0.06
    Activations Density 0.051%

    No Known Activations