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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15-RESID-POST-AA
    6. 57309
    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    长大
    -0.08
    มะ
    -0.07
     Rosenstein
    -0.07
    вести
    -0.07
     Numeric
    -0.07
    ҷ
    -0.07
     Spending
    -0.07
    pst
    -0.07
    訓
    -0.07
     mue
    -0.07
    POSITIVE LOGITS
    ground
    0.07
    _js
    0.07
    会影响到
    0.07
     =>
    0.07
    dater
    0.07
     society
    0.07
    yleft
    0.07
     runner
    0.07
    innitus
    0.06
    ᵘ
    0.06
    Activations Density 0.001%

    No Known Activations