© 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. 15-RESID-POST-AA
    11. 76111
    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
     Simpson
    -0.07
    .u
    -0.07
     tolerance
    -0.07
     transforms
    -0.07
    -0.07
    修复
    -0.07
    ITUDE
    -0.07
    %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
    -0.06
    _issue
    -0.06
     שיה
    -0.06
    POSITIVE LOGITS
    hort
    0.09
    out
    0.07
    ocket
    0.07
    �
    0.07
    嘴角
    0.07
    getExtension
    0.07
     marginRight
    0.07
     driveway
    0.07
     avere
    0.06
    atchet
    0.06
    Activations Density 0.418%

    No Known Activations