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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 15-RESID-POST-AA
    6. 115344
    Prev
    Next
    INDEX
    Explanations

    code

    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
     Process
    -0.07
    ])),
    -0.07
     Hop
    -0.07
    ㎧
    -0.06
    Risk
    -0.06
    	version
    -0.06
     mycket
    -0.06
     disrupt
    -0.06
    >('
    -0.06
     множество
    -0.06
    POSITIVE LOGITS
    둥
    0.08
    >s
    0.07
    @↵
    0.07
    dom
    0.07
    Unhandled
    0.07
    е�
    0.07
     مجل
    0.07
    童年
    0.07
    ר
    0.07
    Lik
    0.07
    Activations Density 0.059%

    No Known Activations