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. 23-RESID-POST-AA
    6. 130430
    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bugs
    -0.08
    建設
    -0.07
    ignant
    -0.07
     вот
    -0.07
    —the
    -0.07
    饴
    -0.07
     goes
    -0.07
     важно
    -0.07
     Oh
    -0.07
    settings
    -0.07
    POSITIVE LOGITS
     Napoleon
    0.07
    🕞
    0.07
    alez
    0.07
    发育
    0.07
     sund
    0.06
     Ez
    0.06
    歧
    0.06
     Vir
    0.06
     Salisbury
    0.06
    .Sample
    0.06
    Activations Density 0.054%

    No Known Activations