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. 131022
    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
    马克思
    -0.08
    总书记在
    -0.08
    勔
    -0.07
    CONDS
    -0.07
    .network
    -0.07
    以至于
    -0.07
    vk
    -0.07
    Aliases
    -0.07
     exter
    -0.07
     hud
    -0.07
    POSITIVE LOGITS
    Higher
    0.08
    _L
    0.07
    問
    0.07
    odeled
    0.07
     paperback
    0.07
    -established
    0.07
    Russian
    0.07
    -not
    0.07
     Program
    0.07
     sharper
    0.06
    Activations Density 0.013%

    No Known Activations