© 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. 7-RESID-POST-AA
    11. 59995
    Prev
    Next
    INDEX
    Explanations

    rhymes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ﳐ
    -0.08
     luckily
    -0.08
    բ
    -0.07
     --->
    -0.07
    Ｍ
    -0.07
     scn
    -0.07
    RETURN
    -0.07
     MSR
    -0.07
     mov
    -0.07
     ken
    -0.07
    POSITIVE LOGITS
    זית
    0.08
    eline
    0.07
     rhs
    0.07
     Giuliani
    0.07
    一个小
    0.07
     enamel
    0.07
    .xxx
    0.07
     rh
    0.07
    rians
    0.06
    iate
    0.06
    Activations Density 0.005%

    No Known Activations