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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 72022
    Prev
    Next
    INDEX
    Explanations

    except

    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
    eled
    -0.07
     Ecuador
    -0.07
     eman
    -0.06
    一辆
    -0.06
    𝘿
    -0.06
    IVED
    -0.06
     ledger
    -0.06
    英雄
    -0.06
     protest
    -0.06
    pushViewController
    -0.06
    POSITIVE LOGITS
    ум
    0.07
    תח
    0.07
    .choice
    0.07
    -sm
    0.07
     worry
    0.06
     umie
    0.06
     advice
    0.06
     rnn
    0.06
     �
    0.06
     этой
    0.06
    Activations Density 0.021%

    No Known Activations