© 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. 11504
    Prev
    Next
    INDEX
    Explanations

    "ified" or "ated" endings

    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_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
     بشأن
    -0.08
     Sylv
    -0.07
    aire
    -0.07
    angkan
    -0.07
    .Sound
    -0.07
    な
    -0.06
     articles
    -0.06
    VALID
    -0.06
    Sparse
    -0.06
     ngoài
    -0.06
    POSITIVE LOGITS
    merican
    0.07
    .Fecha
    0.07
    QUIRED
    0.07
    uracion
    0.07
    켠
    0.07
     psychologically
    0.07
    uestos
    0.07
    \models
    0.07
    dığında
    0.06
    ponses
    0.06
    Activations Density 0.029%

    No Known Activations