© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 120582
    Prev
    Next
    INDEX
    Explanations

    Scientific/technical writing

    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
    还挺
    -0.08
    是最
    -0.07
    㥄
    -0.07
     dod
    -0.07
     conducting
    -0.07
    =g
    -0.07
     fate
    -0.06
    总算
    -0.06
    绤
    -0.06
     për
    -0.06
    POSITIVE LOGITS
    .Conv
    0.08
     dee
    0.08
    Die
    0.07
    layui
    0.07
    Kay
    0.07
    /lic
    0.07
    .Spring
    0.07
     Lisbon
    0.07
    的画面
    0.07
    不适
    0.07
    Activations Density 0.146%

    No Known Activations