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. 2285
    Prev
    Next
    INDEX
    Explanations

    thumb

    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
    伤害
    -0.07
    多种
    -0.07
    estyle
    -0.07
    将进一步
    -0.07
    Mode
    -0.07
    航空航天
    -0.07
    ('.'
    -0.07
    ----------------------------------------------------------------------
    -0.07
    買い
    -0.07
    如下
    -0.07
    POSITIVE LOGITS
    ڜ
    0.07
     graduates
    0.07
     teenager
    0.06
     })).
    0.06
     yaşayan
    0.06
    muş
    0.06
     pulumi
    0.06
     турист
    0.06
     pued
    0.06
    beb
    0.06
    Activations Density 0.003%

    No Known Activations