© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 129955
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    てくれ
    -0.08
     Gilbert
    -0.08
     Excellence
    -0.08
    大规模
    -0.07
    Waiting
    -0.07
     rượu
    -0.07
     Saúde
    -0.07
    ijke
    -0.07
     nationwide
    -0.07
     intoxicated
    -0.07
    POSITIVE LOGITS
    ]));
    0.08
    .c
    0.07
     oa
    0.07
    畖
    0.07
     civ
    0.07
    Ҡ
    0.07
    猺
    0.07
    /<?
    0.07
    ****/↵
    0.07
    =sys
    0.07
    Activations Density 0.010%

    No Known Activations