© 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. 76331
    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
    dez
    -0.07
    UNET
    -0.07
    omidou
    -0.06
     нед
    -0.06
    针对性
    -0.06
    !:
    -0.06
     fly
    -0.06
    ڠ
    -0.06
    菟
    -0.06
    <count
    -0.06
    POSITIVE LOGITS
    -conf
    0.08
     resistant
    0.07
     affirm
    0.07
     threatening
    0.07
    _REQ
    0.07
     knitting
    0.07
    -"
    0.07
     ואין
    0.07
     SIZE
    0.07
    _FEED
    0.07
    Activations Density 0.007%

    No Known Activations