© 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. 15-RESID-POST-AA
    11. 111252
    Prev
    Next
    INDEX
    Explanations

    relevant and appropriate

    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
     Continuous
    -0.08
    ሁ
    -0.07
    Ⲁ
    -0.07
     предостав
    -0.07
    OUS
    -0.07
     abusing
    -0.07
     afr
    -0.07
    ]);
↵
↵
    -0.06
    pricing
    -0.06
     dearly
    -0.06
    POSITIVE LOGITS
    ły
    0.09
     historia
    0.08
    enze
    0.07
    ちは
    0.07
    _calendar
    0.07
    liśmy
    0.07
    etta
    0.07
     dicho
    0.07
    =in
    0.06
    ила
    0.06
    Activations Density 0.024%

    No Known Activations