Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 31315
    Prev
    Next
    INDEX
    Explanations

    community, rights, faith, health

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    院院士
    -0.07
    -bedroom
    -0.07
    %=
    -0.07
    颞
    -0.06
    ({})↵
    -0.06
     empath
    -0.06
     welcoming
    -0.06
    Portland
    -0.06
    焊
    -0.06
     volatile
    -0.06
    POSITIVE LOGITS
    _album
    0.08
    后果
    0.07
    _OVER
    0.07
    Ctr
    0.07
    .Menu
    0.07
     ACTION
    0.07
    music
    0.07
    	packet
    0.07
    BLE
    0.06
    ︺
    0.06
    Activations Density 0.751%

    No Known Activations