© 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. 76702
    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
     childhood
    -0.07
    imulation
    -0.07
     semaine
    -0.06
    褓
    -0.06
    =session
    -0.06
    @author
    -0.06
    ﮌ
    -0.06
    ahun
    -0.06
    -invalid
    -0.06
    湝
    -0.06
    POSITIVE LOGITS
    .parameter
    0.08
     VLC
    0.07
    ﹤
    0.07
     TCP
    0.07
    Tra
    0.07
    当选
    0.07
     entra
    0.07
     Alta
    0.07
    |$
    0.07
    �니다
    0.07
    Activations Density 0.005%

    No Known Activations