© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 59586
    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
    Negative Logits
    ὥ
    -0.08
    Parm
    -0.07
     AFF
    -0.07
     того
    -0.07
    .python
    -0.07
    cient
    -0.07
     Intr
    -0.06
     length
    -0.06
     prof
    -0.06
    เข
    -0.06
    POSITIVE LOGITS
    osos
    0.07
     Meetings
    0.07
    rift
    0.07
    =head
    0.07
    .intersection
    0.07
    مشاكل
    0.07
     frustrated
    0.06
    Effects
    0.06
    ﭰ
    0.06
    *S
    0.06
    Activations Density 0.001%

    No Known Activations