© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 75037
    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
    ڛ
    -0.07
    '",
    -0.07
    ää
    -0.07
    .getLeft
    -0.07
     composing
    -0.07
    [
    -0.07
    חוף
    -0.07
    ored
    -0.07
     UserManager
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     initiation
    0.08
    甩
    0.07
     refusal
    0.07
     deny
    0.07
     theft
    0.07
    _GL
    0.07
     sanity
    0.07
     UNIX
    0.07
     LOSS
    0.07
     criticism
    0.07
    Activations Density 0.003%

    No Known Activations