© 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. 41570
    Prev
    Next
    INDEX
    Explanations

    Errors and contradictions

    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
    グ
    -0.07
     monday
    -0.07
    managed
    -0.06
    海外
    -0.06
     xtype
    -0.06
     зарегист
    -0.06
    .long
    -0.06
     adaptable
    -0.06
    .ResponseBody
    -0.06
     Blowjob
    -0.06
    POSITIVE LOGITS
    (Connection
    0.07
    Players
    0.07
    头皮
    0.07
    ension
    0.07
     Sexo
    0.07
     predicted
    0.07
    illary
    0.06
    ⎠
    0.06
    假装
    0.06
    间隔
    0.06
    Activations Density 0.150%

    No Known Activations