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. 15-RESID-POST-AA
    6. 27523
    Prev
    Next
    INDEX
    Explanations

    photographic

    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
     December
    -0.07
    	RTCK
    -0.07
     corpus
    -0.07
     Bene
    -0.06
    Remote
    -0.06
    Overview
    -0.06
    �
    -0.06
     znajdu
    -0.06
    OLER
    -0.06
    Coder
    -0.06
    POSITIVE LOGITS
    高额
    0.08
     Feng
    0.07
    _SCHED
    0.07
    .Cos
    0.07
    מרים
    0.07
    飙升
    0.07
     outros
    0.07
    uctor
    0.07
     softened
    0.07
    _encoded
    0.07
    Activations Density 0.002%

    No Known Activations