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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 84707
    Prev
    Next
    INDEX
    Explanations

    sleeping on the floor

    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
     вкус
    -0.07
    agner
    -0.07
    AAC
    -0.07
    (Sub
    -0.06
    .fits
    -0.06
     احد
    -0.06
    _nn
    -0.06
    槠
    -0.06
    _grp
    -0.06
    _EMP
    -0.06
    POSITIVE LOGITS
     }</
    0.07
     pomiędzy
    0.07
    時候
    0.07
    "profile
    0.07
     Öl
    0.07
     случа
    0.06
     meinen
    0.06
    夠
    0.06
     }}>↵
    0.06
    backs
    0.06
    Activations Density 0.022%

    No Known Activations