© 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. 19-RESID-POST-AA
    11. 110168
    Prev
    Next
    INDEX
    Explanations

    |

    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
    	range
    -0.08
    �
    -0.07
    辏
    -0.07
     taken
    -0.07
    .argv
    -0.07
    SearchParams
    -0.07
    玳
    -0.07
    Dig
    -0.07
    揶
    -0.07
    .Var
    -0.07
    POSITIVE LOGITS
     honors
    0.08
     ;↵
    0.07
     patriotic
    0.07
    	y
    0.07
    _THIS
    0.07
     convictions
    0.07
     creates
    0.07
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.06
     TEMP
    0.06
     competency
    0.06
    Activations Density 0.002%

    No Known Activations