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. 56559
    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
     tvb
    -0.08
     הצי
    -0.07
    .The
    -0.07
     Jazz
    -0.06
     tuổi
    -0.06
    🕴
    -0.06
     direkt
    -0.06
    _ev
    -0.06
    밴
    -0.06
     UIManager
    -0.06
    POSITIVE LOGITS
     Sch
    0.07
    _accum
    0.07
    tors
    0.07
    과
    0.06
    ographics
    0.06
     우리가
    0.06
    arding
    0.06
    效率
    0.06
    _formats
    0.06
    OfDay
    0.06
    Activations Density 0.012%

    No Known Activations